Finding and understanding pedal misapplication crashes using a deep learning natural language model

Bareiss, Max; Smith, Colin; Gabler, Hampton C.

doi:10.1080/15389588.2021.1982616

Cited by 5 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike previous studies [ 19 , 23 ], this work did not use foot position data and driver physiological data as model inputs but instead used driving data [ 34 ] collected by acquisition modules such as OBD or CAN as inputs. Therefore, the optimal accuracy of our model was 1.87% and 6.18% higher than the detection models established by Bareiss et al and Wu et al, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, Bareiss et al analyzed the crash data from NWVCSS and North Carolina, manually classified the data into normal braking and pedal misuse, and built a classification model using the Bidirectional Encoder Representations from Transformers (BERT) natural language understanding model. Referring to the model of the sequence library, the fine-tuned model had a classification accuracy of 95.7% [ 23 ].…”

Section: Related Workmentioning

confidence: 99%

“…These studies have demonstrated the effect of pedal construction design [ 14 ], age and gender [ 15 , 16 , 17 ], shoe contact area with the pedal, single/dual foot operation mode, foot position [ 18 , 19 ], and driver cognitive function [ 20 , 21 ] on pedal misapplication. Currently, studies on pedal misapplication rely mainly on questionnaire surveys [ 22 ], analysis of vehicle driving data [ 23 ], driver physiological data [ 15 ], video-based foot motion trajectory [ 19 ], and combinations of vehicle driving data and foot posture data [ 12 , 13 , 19 , 20 ]. However, the last three types of data are relatively difficult to acquire during naturalistic driving as they require body posture sensors and medical physiometer devices, which are not usually found in vehicles.…”

Section: Introductionmentioning

confidence: 99%

“…Benefiting from significant advancements in computer computing power and the development in the deep learning domain, Convolution Neural Networks (CNNs) are increasingly used in driver behavior recognition tasks. These tasks include braking intention recognition [ 24 ], pedal misapplication detection [ 23 , 25 ], driver distraction detection [ 26 , 27 , 28 ], fatigue detection [ 29 ], and so on. However, there is a limited number of studies that have used deep learning to detect pedal misapplication by electric bus drivers, moreover, using the foot camera-based scene data images may encounter problems as they are easily affected by lighting and angle.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Electric Bus Pedal Misapplication Detection Based on Phase Space Reconstruction Method

Lyu,

Li,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Due to the environmental protection of electric buses, they are gradually replacing traditional fuel buses. Several previous studies have found that accidents related to electric vehicles are linked to Unintended Acceleration (UA), which is mostly caused by the driver pressing the wrong pedal. Therefore, this study proposed a Model for Detecting Pedal Misapplication in Electric Buses (MDPMEB). In this work, natural driving experiments for urban electric buses and pedal misapplication simulation experiments were carried out in a closed field; furthermore, a phase space reconstruction method was introduced, based on chaos theory, to map sequence data to a high-dimensional space in order to produce normal braking and pedal misapplication image datasets. Based on these findings, a modified Swin Transformer network was built. To prevent the model from overfitting when considering small sample data and to improve the generalization ability of the model, it was pre-trained using a publicly available dataset; moreover, the weights of the prior knowledge model were loaded into the model for training. The proposed model was also compared to machine learning and Convolutional Neural Networks (CNN) algorithms. This study showed that this model was able to detect normal braking and pedal misapplication behavior accurately and quickly, and the accuracy rate on the test dataset is 97.58%, which is 9.17% and 4.5% higher than the machine learning algorithm and CNN algorithm, respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Electric Bus Pedal Misapplication Detection Based on Phase Space Reconstruction Method

Lyu,

Li,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Despite the effectiveness of the model, to the best of the authors' knowledge, a few studies have used BERT to interpret traffic crash descriptions and classify the associated word meanings. Bareiss et al [55] collected data from more than 9700 crash instances to train and validate a BERT-based text classification model for identifying pedal misapplication. When applied to the test dataset, the proposed BERT model reportedly demonstrated a classification accuracy of 95% for the four classes.…”

Section: Literature Reviewmentioning

confidence: 99%

Text Classification Modeling Approach on Imbalanced-Unstructured Traffic Accident Descriptions Data

Seo,

Park,

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

The unstructured-textual crash descriptions recorded by police officers is rarely utilized, despite containing detailed information on traffic situations. This lack of utilization is mainly due to the difficulty in analyzing text data, as there is currently no innovative methodology for extracting meaningful information from it. Given limitations and challenges in analyzing traffic crash descriptions, this study developed a methodology to classify significant words in unstructured data that describe traffic crash scenarios into standardized data. Ultimately, a natural language processing technique, specifically a bidirectional encoder representation from transformer (BERT), was used to extract meaningful information from crash descriptions. This BERT-based model effectively extracts information on the exact collision point and the pre-crash vehicle maneuver from crash descriptions. Its practical approach allows for the interpretation of traffic crash descriptions and outperforms other natural language processing models. Importantly, this method of extracting crash scene information from traffic crash descriptions can aid in better comprehending the unique characteristics of traffic crashes. This comprehension can ultimately aid in the development of appropriate countermeasures, leading to the prevention of future traffic crashes.

show abstract

Railway accident causation prediction with improved transformer model based on lexical information and contextual relationships

Jiang,

Wang

2024

Knowledge-Based Systems

View full text Add to dashboard Cite

Finding and understanding pedal misapplication crashes using a deep learning natural language model

Cited by 5 publications

References 2 publications

Electric Bus Pedal Misapplication Detection Based on Phase Space Reconstruction Method

Electric Bus Pedal Misapplication Detection Based on Phase Space Reconstruction Method

Text Classification Modeling Approach on Imbalanced-Unstructured Traffic Accident Descriptions Data

Railway accident causation prediction with improved transformer model based on lexical information and contextual relationships

Contact Info

Product

Resources

About