Driving event detection and driving style classification using artificial neural networks

Brombacher, Patrick; Masino, Johannes; Frey, Michael; Gauterin, Frank

doi:10.1109/icit.2017.7915497

Cited by 57 publications

(39 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, we only found one study where experts applied a data-driven approach to detect driving styles, such as sporty, normal, and defensive. However, the authors did not report how many experts were involved in the data labeling and the inter-rater reliability reached among experts [33]. In our study, 15 experts labeled the dataset, by assigning a class (i.e., calm, normal or aggressive) to each driver.…”

Section: A Six-step Methodology For Driving-styles Classificationmentioning

confidence: 89%

“…This input is usually combined with other inputs, such as speed [30], deceleration [31], and steering [32]. In addition, longitudinal and lateral acceleration input has been used to capture the way a driver turns or changes a lane [15,33]. Other inputs that are also considered in order to identify driving styles are sudden acceleration and braking [34,35].…”

Section: Feature Space or Inputmentioning

confidence: 99%

“…Some studies have established an additional label, arguing that drivers may reveal calm and aggressive driving styles at the same time during a route; the driver can, therefore, be labeled as calm, normal, moderate, or aggressive [9,16]. In addition, some studies have reported four or more categories (e.g., a five-point scale from very sporty to very defensive [33] and a four-point scale from below normal to very aggressive [5]), but they are rarely used, as the number of labels impacts the accuracy of the model and affects its interpretation.…”

Section: Outputmentioning

confidence: 99%

“…Two factors should be considered when designing ANN models: (1) the selection of the training algorithm; and (2) the network architecture [53]. In this work, we selected the backpropagation algorithm as the training algorithm, because it had shown good classification results [12,33]. For the network architecture, the following parameters should be tuned: (i) the number of hidden layers; (ii) the activation function; (iii) the number of max iterations; (iv) the learning rate (lr); and (v) the number of neurons (N) for the hidden layer.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 3 more Smart Citations

A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification

Silva

Naranjo

2020

Sensors

View full text Add to dashboard Cite

Identifying driving styles using classification models with in-vehicle data can provide automated feedback to drivers on their driving behavior, particularly if they are driving safely. Although several classification models have been developed for this purpose, there is no consensus on which classifier performs better at identifying driving styles. Therefore, more research is needed to evaluate classification models by comparing performance metrics. In this paper, a data-driven machine-learning methodology for classifying driving styles is introduced. This methodology is grounded in well-established machine-learning (ML) methods and literature related to driving-styles research. The methodology is illustrated through a study involving data collected from 50 drivers from two different cities in a naturalistic setting. Five features were extracted from the raw data. Fifteen experts were involved in the data labeling to derive the ground truth of the dataset. The dataset fed five different models (Support Vector Machines (SVM), Artificial Neural Networks (ANN), fuzzy logic, k-Nearest Neighbor (kNN), and Random Forests (RF)). These models were evaluated in terms of a set of performance metrics and statistical tests. The experimental results from performance metrics showed that SVM outperformed the other four models, achieving an average accuracy of 0.96, F1-Score of 0.9595, Area Under the Curve (AUC) of 0.9730, and Kappa of 0.9375. In addition, Wilcoxon tests indicated that ANN predicts differently to the other four models. These promising results demonstrate that the proposed methodology may support researchers in making informed decisions about which ML model performs better for driving-styles classification.Sensors 2020, 20, 1692 2 of 21 and ultimately minimizing traffic incidents [8]. Many potential applications that utilize driving-style recognition are being developed [9]. For example, insurance companies are developing automatic ways to ascertain driving styles of their clients in order to offer the right policy [10]. In addition, in the area of advanced driver-assistance systems (ADAS), researchers are interested in the development of intelligent tools to provide tailored feedback according to the driver's behavior [11].Current studies have reported different methodologies to classify driving styles using in-vehicle data. These methodologies mostly depend on (i) the inputs that can be extracted and derived from the data gathered (e.g., acceleration, deceleration, brake) [12,13]; (ii) the computational models to classify driving styles [14,15]; (iii) driving-styles outputs (e.g., calm, normal, aggressive) [16,17]; and (iv) the performance metrics that evaluate these models [18,19]. Although these studies show a growing interest in classifying driving styles empirically, few studies have systematically evaluated which inputs and models are better predictors of a particular driving style's output.The existing body of research has attempted to evaluate several computational models to identify driving styles usin...

show abstract

Section: A Six-step Methodology For Driving-styles Classificationmentioning

confidence: 89%

Section: Feature Space or Inputmentioning

confidence: 99%

Section: Outputmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%

See 2 more Smart Citations

A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification

Silva

Naranjo

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Brombacher et al used an artificial neural network to calculate aggressive scores for driving styles. According to the detected driving events, the overall driving style is divided into five types [13]. Xie et al utilized a random forest as the style classification model for maneuver-based driving behaviors [14].…”

Section: Introductionmentioning

confidence: 99%

A Semi-Supervised Tri-CatBoost Method for Driving Style Recognition

et al. 2020

View full text Add to dashboard Cite

Driving style recognition plays a key role in ensuring driving safety and improving vehicle traffic efficiency. With the development of sensing technology, data-driven methods are more widely uesd to recognize driving style. However, adequately labeling data is difficult for supervised learning methods, while the classification accuracy is not sufficiently approved for unsupervised learning methods. This paper proposes a new driving style recognition method based on Tri-CatBoost, which takes CatBoost as base classifier and effectively utilizes the semi-supervised learning mechanism to reduce the dependency on data labels and improve the recognition ability. First, statistical features were extracted from the velocity, acceleration and jerk signals to fully characterize the driving style. The kernel principal component analysis was used to perform nonlinear feature dimension reduction to eliminate feature coupling. CatBoost is an ensemble of symmetric decision trees whose symmetry structure endows it fewer parameters, faster training and testing, and a higher accuracy. Then, a Tri-Training strategy is employed to integrate the base CatBoost classifiers and fully exploit the unlabeled data to generate pseudo-labels, by which the base CatBoost classifiers are optimized. To verify the effectiveness of the proposed method, a large number of experiments are performed on the UAH DriveSet. When the labeling ratio is 50%, the macro precision of Tri-CatBoost is 0.721, which is 15.7% higher than that of unsupervised K-means, 1.6% higher than that of supervised GBDT, 3.7% higher than that of Self-Training, 0.7% higher than that of Co-training, 1.5% higher than that of random forest, 6.7% higher than that of decision tree, and 4.0% higher than that of multilayer perceptron. The macro recall of Tri-CatBoost is 0.744, which is also higher than other methods. The experimental results fully demonstrate the superiority of this work in reducing label dependency and improving recognition performance, which indicates that the proposed method has broad application prospects.

show abstract

An abnormal driving behavior recognition algorithm based on the temporal convolutional network and soft thresholding

Zhao

Jia

Luo

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Most traffic accidents are caused by bad driving habits. Online monitoring of the abnormal driving behaviors of drivers can help reduce traffic accidents. Recently, abnormal driving behavior recognition based on the sensors' data embedded in commodity smartphones has attracted much attention. Though much progress has been made about driving behavior recognition, the existing works cannot achieve high recognition accuracy and show poor robustness. To improve the driving behaviors recognition accuracy and robustness, we propose an algorithm based on Soft Thresholding and Temporal Convolutional Network (S‐TCN) for driving behavior recognition. In this algorithm, we first introduce a soft attention mechanism to learn the importance of different sensors. The TCN has the advantages of small memory requirement and high computational efficiency. And the soft thresholding can further filter the redundant features and extract the main features. So, we fuse the TCN and soft thresholding to improve the model's stability and accuracy. Our proposed model is extensively evaluated on four real public data sets. The experimental results show that our proposed model outperforms best state‐of‐the‐art baselines by 2.24%.

show abstract

Driving event detection and driving style classification using artificial neural networks

Cited by 57 publications

References 10 publications

A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification

A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification

A Semi-Supervised Tri-CatBoost Method for Driving Style Recognition

An abnormal driving behavior recognition algorithm based on the temporal convolutional network and soft thresholding

Contact Info

Product

Resources

About