NN-based measurements for driving pattern classification

Lecce, Vincenzo Di; Calabrese, Marco

doi:10.1109/imtc.2009.5168455

Cited by 7 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shi, et al [27] proposed a way of driving style identification and used neural networks to learn driver features and different driving styles. Similarly, Di Lecce and Calabrese [28] studied and classified the driving style into several categories using neural networks. In particular, a multilayer perceptron with back-propagation learning algorithm is used in their study.…”

Section: Driving Behavior Classification and Predictionmentioning

confidence: 99%

A Deep Learning Based Model for Driving Risk Assessment

Bian

Lee

Zhao

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In this paper a novel multilayer model is proposed for assessing driving risk. Studying aggressive behavior via massive driving data is essential for protecting road traffic safety and reducing losses of human life and property in smart city context. In particular, identifying aggressive behavior and driving risk are multi-factors combined evaluation process, which must be processed with time and environment. For instance, improper time and environment may facilitate abnormal driving behavior. The proposed Dynamic Multilayer Model consists of identifying instant aggressive driving behavior that can be visited within specific time windows and calculating individual driving risk via Deep Neural Networks based classification algorithms. Validation results show that the proposed methods are particularly effective for identifying driving aggressiveness and risk level via real dataset of 2129 drivers' driving behavior.

show abstract

Section: Driving Behavior Classification and Predictionmentioning

confidence: 99%

A Deep Learning Based Model for Driving Risk Assessment

Bian

Lee

Zhao

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Rygula [18] developed a driving style identification method for driver sleepiness and fatigue detection based on speed and acceleration distribution. Di Lecce and Calabrese [19] classified the driving pattern into forward acceleration, forward breaking, curve entering, curve leaving and car overtaking using neural networks. However, these works focused only on the overall differences in driving behaviour and the individual driving style of various drivers was not excavated.…”

Section: Iet Intelligent Transport Systemsmentioning

confidence: 99%

Leveraging longitudinal driving behaviour data with data mining techniques for driving style analysis

et al. 2015

IET Intelligent Transport Systems

View full text Add to dashboard Cite

Accurately understanding driving behaviour is of crucial importance for advanced driving assistant systems such as adaptive cruise control system and intelligent forward collision warning system. To understand different driving styles, this study employs the clustering method and topic model to extract latent driving states, which can elaborate and analyse the commonness and individuality of driving behaviour characteristics with the longitudinal driving behaviour data collected by the instrumented vehicle. To handle the large set of data and discover the valuable knowledge, the data mining techniques including ensemble clustering method based on the kernel fuzzy C-means algorithm and the modified latent Dirichlet allocation model are employed in this study. The 'aggressive', 'cautious' and 'moderate' driving states are discovered and the underlying quantified structure is built for the driving style analysis.

show abstract

“…A Neural Network (NN)-based model for driving pattern classification is proposed by [12]. Bi-axial accelerometer and GPS data are combined to characterize driving patterns using neural networks.…”

Section: Related Workmentioning

confidence: 99%

“…recognise driver manoeuvres from data sensors rule based [9] machine learning framework for modelling and recognizing driver manoeuvres graphical models, HMMs and CHMMs [10] adaptive assistance system to determine/predict drivers' behaviour HMM [11] classify driving patterns using neural networks neural networks [12] evaluate the comfort in public transportation three algorithms: Threshold detection, jerk detection and Comfort index measurement [13] record driving events and detect unsafe driving behaviours Fuzzy Logic [14] monitor road and traffic conditions using mobile Smartphones threshold detection [15] understand the driver behaviour using Smartphone sensors endpoint detection, DTW, Bayesian classification [16] detect and alert dangerous vehicle manoeuvres related to drunk driving pattern recognition [17] investigate driver behaviour as safe or unsafe DTW, Bayesian classification [6] III. MODEL DESIGN This section discusses two models that combine speed and acceleration into an erratic driving detection system.…”

Section: Goals Of Behaviour Modelling Systemmentioning

confidence: 99%

Combining speed and acceleration to detect reckless driving in the informal public transport industry

Zeeman

Booysen

2013

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)

View full text Add to dashboard Cite

Abstract-The informal transport industry in Sub-Saharan Africa is notoriously dangerous, leading to many fatalities annually. This paper presents an innovative way of monitoring driver behaviour, in real-time, by taking into account road design standards, vehicle dynamics, and passenger comfort. Two models are presented that each combines acceleration and speed data into an erratic driving detection algorithm. The first model is developed though the evaluation of empirical results taken from trips in a minibus taxi, and subjectively gauging recklessness from a passenger's perspective. The second model presents a novel use of commonly used civil engineering principles, used in road design. Evaluation of the models, using actual minibus data, demonstrates that both successfully detect reckless driving, but the second model proves to be simpler and less processor intensive.

show abstract

NN-based measurements for driving pattern classification

Cited by 7 publications

References 18 publications

A Deep Learning Based Model for Driving Risk Assessment

A Deep Learning Based Model for Driving Risk Assessment

Leveraging longitudinal driving behaviour data with data mining techniques for driving style analysis

Combining speed and acceleration to detect reckless driving in the informal public transport industry

Contact Info

Product

Resources

About