Public Transport Driver Identification System Using Histogram of Acceleration Data

Virojboonkiate, Nuttun; Chanakitkarnchok, Adsadawut; Vateekul, Peerapon; Rojviboonchai, Kultida

doi:10.1155/2019/6372597

Cited by 14 publications

(21 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we found that gyroscope and accelerometer data for 2 hours and 10 minutes per driver are sufficient to solve the same problem. Also, unlike [17] that suggested avoiding the z-axis, our results show that the highest performance achieved using data from all axes. xyz-Ac.…”

Section: A Sensitivity Analysis On Involved Axiscontrasting

confidence: 52%

“…• To train the GAN model, DWT of 6 signals of threedimensional accelerometer and gyroscope sensors data are fed to a specialized GAN to generate some augmented drivers' data. • In the feature extraction phase, we apply histograms of acceleration and gyroscope signals on overlapped win-dows, while [17] used only acceleration data. Although the GAN model works on DWT of driving data and yields promising results, the histogram feature overcomes DWT, spectral, temporal, and other statistical features for the driver identification phase.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors

Ahmadian¹,

Ghatee²,

Wahlström³

2021

Preprint

View full text Add to dashboard Cite

Driver identification is an important research area in intelligent transportation systems, with applications in commercial freight transport and usage-based insurance. One way to perform the identification is to use smartphones as sensor devices. By extracting features from smartphone-embedded sensors, various machine learning methods can identify the driver. The identification becomes particularly challenging when the number of drivers increases. In this situation, there is often not enough data for successful driver identification. This paper uses a Generative Adversarial Network (GAN) for data augmentation to solve the problem of lacking data. Since GAN diversifies the drivers' data, it extends the applicability of the driver identification. Although GANs are commonly used in image processing for image augmentation, their use for driving signal augmentation is novel. Our experiments prove their utility in generating driving signals emanating from the Discrete Wavelet Transform (DWT) on smartphones' accelerometer and gyroscope signals. After collecting the augmented data, their histograms along the overlapped windows are fed to machine learning methods covered by a Stacked Generalization Method (SGM). The presented hybrid GAN-SGM approach identifies drivers with 97% accuracy, 98% precision, 97% recall, and 97% F1-measure that outperforms standard machine learning methods that process features extracted by the statistical, spectral, and temporal approaches.

show abstract

Section: A Sensitivity Analysis On Involved Axiscontrasting

confidence: 52%

mentioning

confidence: 99%

Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors

Ahmadian¹,

Ghatee²,

Wahlström³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…(ii) Driver factors. Virojboonkiate et al (2019) [44] proposed a driver identification system based on acceleration sensor data for PT systems. Mokarami et al (2019) [45] investigated 336 PT bus drivers in Tehran with two questionnaires and indicated that the organizational safety culture had positive effects on decreasing the unsafe behaviours of PT drivers and reducing PT accidents.…”

Section: Transportation Factormentioning

confidence: 99%

“…Based on Formulas (36) and (41), the individual value of the passenger for the energy factor during the time period t 1 ∼ t m can be calculated by Formula (44):…”

Section: Passenger Utility Analysesmentioning

confidence: 99%

Multiple Utility Analyses for Sustainable Public Transport Planning and Management: Evidence from GPS-Equipped Taxi Data in Haikou

Gui

2020

Sustainability

View full text Add to dashboard Cite

The transportation utility values calculated by traditional utility methods are not comprehensive. Some objects and factors are ignored in traditional utility methods, and this narrow perspective is their primary drawback. In intelligent transportation systems, it is necessary to calculate transportation utility for promoting public traffic planning and management. To build a sustainable intelligent transportation system, modified utility methods are essential to analyze transportation utility in a comprehensive way with innovative technologies and efficient communication systems. To solve the disadvantages of traditional utility methods, it is necessary to establish a new method to build sustainable public transport in the future. In this study, the Multiple Utility Method and Transportation Utility Method are proposed for public transport planning and management from multiple perspectives. A sample is presented to provide a better description, and 69,174 GPS-equipped taxi data in Haikou are adopted for the application of the Transportation Utility Method. The results show that the transportation utility values calculated by the Transportation Utility Method are more comprehensive than the transportation utility calculated by traditional utility methods. This indicates that it is necessary to calculate transportation utility from multiple perspectives based on the Transportation Utility Method. Future directions could include improving the methods, considering more factors, expanding the data used, and extrapolating this research to other cities around the world with similar urban metrics and urban form.

show abstract

“…After performing feature construction and feature selection, the sample features were input into a model integrating support vector machine (SVM), K‐nearest neighbours (KNNs), RF, and decision‐making trees (DT) with hyperparameter tuning, where the recognition accuracy rate was 88%. In [19, 20], a backward propagation (BP) neural network was used as the classifier, while the accelerator pedal and brake pressure signals or some improved features of vehicle acceleration were selected as the model input.…”

Section: Introductionmentioning

confidence: 99%

Driver identification using 1D convolutional neural networks with vehicular CAN signals

Liu

Gao

et al. 2020

IET intell. transp. syst

View full text Add to dashboard Cite

This study proposes a deep learning framework for driver identity identification by extracting information from the vehicular controller area network (CAN) bus signals. First, naturalistic driving data of 20 drivers were collected under a fixed testing route with different road types and different traffic conditions. Then, a one‐dimensional convolutional neural network was constructed for driver identification, which consists of two convolutional‐pooling layers, a fully connected layer, and a SoftMax layer. Model optimisation algorithms were applied to improve accuracy and speed up the training process. Also, the model parameters were optimised by evaluating their influences on the model results. Furthermore, the performance of the proposed algorithm was compared with that of the K‐nearest neighbour, support vector machine, multi‐layer perceptron, and long short‐term memory model. The authors used the MacrothinmathspaceF1 score as an evaluation criterion and the identification score of the authors' proposed model reaches 99.10% under 20 testing subjects where the data time window size is one second and the sample data overlap is 80%. The results show that the model's performance is significantly better than the other algorithms, which can effectively identify driver identities with stability and robustness.

show abstract

Public Transport Driver Identification System Using Histogram of Acceleration Data

Cited by 14 publications

References 15 publications

Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors

Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors

Multiple Utility Analyses for Sustainable Public Transport Planning and Management: Evidence from GPS-Equipped Taxi Data in Haikou

Driver identification using 1D convolutional neural networks with vehicular CAN signals

Contact Info

Product

Resources

About