On the performance of localization prediction methods for vehicular Ad Hoc Networks

Balico, Leandro N.; Oliveira, Horácio A. B. F.; Souza, Efren Lopes; Pazzi, Richard W.; Nakamura, Eduardo F.

doi:10.1109/iscc.2015.7405541

Cited by 15 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many existing works aim at predicting vehicle mobility in the background of selecting a stable wireless link for routing data in vehicle ad-hoc networks [16][17][18]. Agarwal et al proposed a Dead Reckoning mechanism that uses the linear sum of a vehicle's instant position and velocity to predict its near future positions [16].…”

Section: Related Workmentioning

confidence: 99%

“…Agarwal et al proposed a Dead Reckoning mechanism that uses the linear sum of a vehicle's instant position and velocity to predict its near future positions [16]. Balico et al adopted a shallow feedforward neural network with one hidden layer to predict vehicle mobility [17]. Their neural network accepts the instant position and velocity of a vehicle as input, and outputs its predicted next position with a time interval from 0.5 to 2 seconds.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

DeepVM: RNN-Based Vehicle Mobility Prediction to Support Intelligent Vehicle Applications

Liu

Shoji

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

The recent advances in vehicle industry and vehicleto-everything communications are creating a huge potential market of intelligent vehicle applications, and exploiting vehicle mobility is of great importance in this field. Hence, this paper proposes a novel vehicle mobility prediction algorithm to support intelligent vehicle applications. First, a theoretical analysis is given to quantitatively reveal the predictability of vehicle mobility. Based on the knowledge earned from theoretical analysis, a deep recurrent neural network (RNN)-based algorithm called DeepVM is proposed to predict vehicle mobility in a future period of several or tens of minutes. Comprehensive evaluations have been carried out based on the real taxi mobility data in Tokyo, Japan. The results have not only proved the correctness of our theoretical analysis, but also validated that DeepVM can significantly improve the quality of vehicle mobility prediction compared with other state-of-art algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

DeepVM: RNN-Based Vehicle Mobility Prediction to Support Intelligent Vehicle Applications

Liu

Shoji

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…To deal with this problem, vehicles are commonly equipped with global positioning system (GPS) devices that provide location information [1,3,4]. However, the accuracy of GPS information can be affected by dense urban areas, such as urban street canyons and indoor parking lots, because of the absence of direct satellite visibility, which turns the GPS into an inaccurate instrument to provide precise location information [5].…”

Section: Introductionmentioning

confidence: 99%

“…To tackle this drawback, there are some solutions proposed in the literature that use anchor nodes [5]. In these approaches, anchor nodes are aware of their positions, so the other nodes can measure their distances using the anchor nodes as references to compute their relative positions [6].…”

Section: Introductionmentioning

confidence: 99%

Cooperative Localization Improvement Using Distance Information in Vehicular Ad Hoc Networks

Lobo

Grael

Oliveira

et al. 2019

Sensors

View full text Add to dashboard Cite

In vehicular ad hoc networks (VANets), a precise localization system is a crucial factor for several critical safety applications. The global positioning system (GPS) is commonly used to determine the vehicles’ position estimation. However, it has unwanted errors yet that can be worse in some areas, such as urban street canyons and indoor parking lots, making it inaccurate for most critical safety applications. In this work, we present a new position estimation method called cooperative vehicle localization improvement using distance information (CoVaLID), which improves GPS positions of nearby vehicles and minimize their errors through an extended Kalman filter to execute Data Fusion using GPS and distance information. Our solution also uses distance information to assess the position accuracy related to three different aspects: the number of vehicles, vehicle trajectory, and distance information error. For that purpose, we use a weighted average method to put more confidence in distance information given by neighbors closer to the target. We implement and evaluate the performance of CoVaLID using real-world data, as well as discuss the impact of different distance sensors in our proposed solution. Our results clearly show that CoVaLID is capable of reducing the GPS error by 63%, and 53% when compared to the state-of-the-art VANet location improve (VLOCI) algorithm.

show abstract

“…Progressing propels in convenient figuring, remote correspondence and recognizing have enabled the improvement of different entrancing and alluring applications in Intelligent Transportation Systems (ITS). champion among the most charming issues to be appreciated with respect to vehicular frameworks is the methods by which to give extremely correct and trustworthy impediment information wherever and at whatever point [1]. Nowadays, most of the created vehicles are passed on with a Global Positioning System (GPS), and untouchable in vehicle course structures can be presented in exchange vehicles at a reasonable cost.…”

Section: Introductionmentioning

confidence: 99%

Perfomance Evaluation of AODV and DSDV Routing Protocol in Vehicle Adhoc Network With NS2

2019

IJRTE

View full text Add to dashboard Cite

Here, the Limitation frameworks assume a remarkable job in various applications for transport unplanned Networks (VANETs). A standout among-st the foremost intriguing problems to be settled with regards to transport networks is that the manner by that to convey anywhere and whenever terribly precise and dependable restriction knowledge. outstanding attributes of VANETs, as an example, skilfulness needs, driver's conduct and therefore the quick uprooting nature of vehicles cause fast and steady changes in system topology, prompting dispersion of obsolete confinement knowledge. To evade this issue, Associate in Nursing possibility is that the utilization of anticipated future areas of vehicles. The principle thought of this technique is to utilize the restriction expectation as Associate in nursing enlargement of Associate in nursing info combination confinement framework. In such a technique, a destiny role of a automobile is expected for a given destiny time and wont to exploit a destiny time-space window of a vectorial path as in opposition to a static confinement reason. at some stage in this paper, it’s contributed to study this problem by considering and breaking down the employment of restrict expectation as characteristic approach to reinforce VANET programs. It’s contributed to study planned methodologies for confinement, target following and time arrangement expectation systems which will be utilized to assess true and the longer term position of a vehicle. It’s contributed to likewise feature their focal points Associate in nursing impediments through informative dialog imagery its potential application things in VANETs. It’s contributed to gift tons of trials that demonstrate the results of such systems once connected to a sensible VANET.

show abstract

On the performance of localization prediction methods for vehicular Ad Hoc Networks

Cited by 15 publications

References 15 publications

DeepVM: RNN-Based Vehicle Mobility Prediction to Support Intelligent Vehicle Applications

DeepVM: RNN-Based Vehicle Mobility Prediction to Support Intelligent Vehicle Applications

Cooperative Localization Improvement Using Distance Information in Vehicular Ad Hoc Networks

Perfomance Evaluation of AODV and DSDV Routing Protocol in Vehicle Adhoc Network With NS2

Contact Info

Product

Resources

About