To see the other types of publications on this topic, follow the link: Driving behavior recognition.
Journal articles on the topic 'Driving behavior recognition'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Driving behavior recognition.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Liu, Wenlong, Hongtao Li, and Hui Zhang. "Dangerous Driving Behavior Recognition Based on Hand Trajectory." Sustainability 14, no. 19 (2022): 12355. http://dx.doi.org/10.3390/su141912355.
Full textAbstract:
Dangerous driving behaviors in the process of driving will produce road traffic safety hazards, and even cause traffic accidents. Common dangerous driving behavior includes: eating, smoking, fetching items, using a handheld phone, and touching a control monitor. In order to accurately identify the dangerous driving behaviors, this study first uses the hand trajectory data to construct the dangerous driving behavior recognition model based on the dynamic time warping algorithm (DTW) and the longest common sub-sequence algorithm (LCS). Secondly, 45 subjects’ hand trajectory data were obtained by driving simulation test, and 30 subjects’ hand trajectory data were used to determine the dangerous driving behavior label. The matching degree of hand trajectory data of 15 subjects was calculated based on the dangerous driving behavior recognition model, and the threshold of dangerous driving behavior recognition was determined according to the calculation results. Finally, the dangerous driving behavior recognition algorithm and neural network algorithm are compared and analyzed. The dangerous driving behavior recognition algorithm has a fast calculation speed, small memory consumption, and simple program structure. The research results can be applied to dangerous driving behavior recognition and driving distraction warning based on wrist wearable devices.
2
David, Ruth, Sandra Rothe, and Dirk Söffker. "State Machine Approach for Lane Changing Driving Behavior Recognition." Automation 1, no. 1 (2020): 68–79. http://dx.doi.org/10.3390/automation1010006.
Full textAbstract:
Research in understanding human behavior is a growing field within the development of Advanced Driving Assistance Systems (ADASs). In this contribution, a state machine approach is proposed to develop a driving behavior recognition model. The state machine approach is a behavior model based on the current state and a given set of inputs. Transitions to different states occur or we remain in the same state producing outputs. The transition between states depends on a set of environmental and driving variables. Based on a heuristic understanding of driving situations modeled as states, as well as one of the related actions modeling the state, using an assumed relation between them as the state machine topology, in this paper, a crisp approach is applied to adapt the model to real behaviors. An important aspect of the contribution is to introduce a trainable state machine-based model to describe drivers’ lane changing behavior. Three driving maneuvers are defined as states. The training of the model is related to the definition/tuning of transition variables (and state definitions). Here, driving data are used as the input for training. The non-dominated sorting genetic algorithm II is used to generate the optimized transition threshold. Comparing the data of actual human driving behaviors collected using driving simulator experiments and the calculated driving behaviors, this approach is able to develop a personalized behavior recognition model. The newly established algorithm presents an easy to apply, reliable, and interpretable AI approach.
3
Ma, Lijing, Shiru Qu, Lijun Song, Junxi Zhang, and Jie Ren. "Human-like car-following modeling based on online driving style recognition." Electronic Research Archive 31, no. 6 (2023): 3264–90. http://dx.doi.org/10.3934/era.2023165.
Full textAbstract:
<abstract><p>Incorporating human driving style into car-following modeling is critical for achieving higher levels of driving automation. By capturing the characteristics of human driving, it can lead to a more natural and seamless transition from human-driven to automated driving. A clustering approach is introduced that utilized principal component analysis (PCA) and k-means clustering algorithm to identify driving style types such as aggressive, moderate and conservative at the timestep level. Additionally, an online driving style recognition technique is developed based on the memory effect in driving behavior, allowing for real-time identification of a driver's driving style and enabling adaptive control in automated driving. Finally, the Intelligent Driver Model (IDM) has been improved through the incorporation of an online driving style recognition strategy into car-following modeling, resulting in a human-like IDM that emulates real-world driving behaviors. This enhancement has important implications for the field of automated driving, as it allows for greater accuracy and adaptability in modeling human driving behavior and may ultimately lead to more effective and seamless transitions between human-driven and automated driving modes. The results show that the time-step level driving style recognition method provides a more precise understanding of driving styles that accounts for both inter-driver heterogeneity and intra-driver variation. The proposed human-like IDM performs well in capturing driving style characteristics and reproducing driving behavior. The stability of this improved human-like IDM is also confirmed, indicating its reliability and effectiveness. Overall, the research suggests that the proposed model has promising performance and potential applications in the field of automated driving.</p></abstract>
4
Li, Hao, Junyan Han, Shangqing Li, Hanqing Wang, Hui Xiang, and Xiaoyuan Wang. "Abnormal Driving Behavior Recognition Method Based on Smart Phone Sensor and CNN-LSTM." International Journal of Science and Engineering Applications 11, no. 1 (2022): 1–8. http://dx.doi.org/10.7753/ijsea1101.1001.
Full textAbstract:
Accurate identification of abnormal driving behavior is very important to improve driver safety. Aiming at the problem that threshold or traditional machine learning methods are mostly used in existing studies, it is difficult to accurately identify abnormal driving behavior of vehicles, a method of abnormal driving behavior recognition based on smartphone sensor data and convolutional neural network (CNN) combined with long and short-term memory (LSTM) was proposed. Smartphone sensors are used to collect vehicle driving data, and data sets of various driving behaviors are constructed by preprocessing the data. A recognition model based on a convolutional neural network combined with a long short-term memory network was constructed to extract depth features from data sets and recognize abnormal driving behaviors. The test results show that the accuracy of the model based on CNN-LSTM can reach 95.22%, and the performance indexes can reach more than 94%. Compared with the recognition model constructed only by CNN or LSTM, this model has higher recognition accuracy.
5
Zhao, Dengfeng, Yudong Zhong, Zhijun Fu, Junjian Hou, and Mingyuan Zhao. "A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information." Journal of Advanced Transportation 2022 (October 7, 2022): 1–16. http://dx.doi.org/10.1155/2022/7287511.
Full textAbstract:
The frequent traffic accidents lead to a large number of casualties and large related financial losses every year; this serious state is owed to several factors; among those, driving behavior is one of the most imperative subjects to discuss. Driving behaviors mainly include behavior characteristics such as car-following, lane change, and risky driving behavior such as distraction, fatigue, or aggressive driving, which are of great help to various tasks in traffic engineering. An accurate and reliable method of driving behavior recognition is of great significance and guidance for vehicle driving safety. In this paper, the vehicle multisensor information, vehicle CAN bus data acquisition system, and typical feature extraction methods are summarized at first. And then, several driving behavior recognition models based on machine learning and deep learning are reviewed. Through a detailed analysis of the features of random forests, support vector machines, convolutional neural networks, and recurrent neural networks used to build driving behavior recognition models, the following findings are obtained: the driving behavior model constructed by traditional machine learning model is relatively mature but it is greatly affected by feature extraction, data scale, and model structure, which affects the accuracy of the final driving behavior recognition. Deep learning model based on a neural network has achieved high accuracy in identifying driving behavior, and it may gradually become the mainstream of constructing the driving behavior model with the development of big data, artificial intelligence technology, and computer hardware. Finally, this paper points out some content that needs to be further explored, to provide reference and inspiration for scholars in this field to continue to study the driving behavior recognition model in depth.
6
Wei, Jiaxuan, Shuang Yu, and Yu Wang. "Intelligent Driving Behavior Recognition and Legal Liability Issues Using Deep Learning Convolutional Networks." International Journal of Information Technologies and Systems Approach 18, no. 1 (2025): 1–20. https://doi.org/10.4018/ijitsa.382479.
Full textAbstract:
This work aimed to develop a driving behavior recognition and liability assistance determination method applicable to practical traffic safety management and criminal liability determination scenarios. First, an improved deep neural network was designed, which integrated multi-scale 3D convolutional structures and attention mechanisms to efficiently extract driving behavior features from both spatial and temporal dimensions. Next, a subset of six typical driving behaviors was constructed based on the Drive&Act public dataset, followed by sample labeling and feature preprocessing. Finally, based on behavior recognition outputs, a legal article logic mapping model and a behavior risk scoring mechanism were proposed to quantify the legal liability risks corresponding to driving behaviors.
7
Sun, Longxiang, Huanchao Feng, Min Zhang, Anmengdie Li, and Jinglei Zhang. "Distracted Driving Behavior of Operation Recognition Method Based on YOLOv5 and BPNN." Journal of Scientific and Engineering Research 9, no. 4 (2022): 17–26. https://doi.org/10.5281/zenodo.10518762.
Full textAbstract:
<strong>Abstract</strong> In order to accurately identify the driver's distracted driving behavior, reduce the injury of traffic accidents to the personnel in the vehicle and improve the driving safety level, this paper takes the driver's distracted driving behavior as the research object, build a distracted driving experimental environment based on real vehicles, and collected 27902 distracted driving image data of 20 drivers, The combined recognition model of YOLOv5 and BPNN was constructed, the video frame image was input into the trained YOLOv5 model, the boundary box data of the driver's left, right hand and face were output, and then the boundary box data was input into the BPNN model for distracted driving behavior recognition. The precision, recall and F1 score of YOLOv5 and BP NN combined recognition model for operation distraction are 0.926, 0.930 and 0.928 respectively, and the overall macro F1 of the model is 0.938. Compared with other similar studies, this model has stronger recognition performance. The research on distracted driving recognition method in this paper provides a certain theoretical basis and method for the improvement of vehicle active safety early warning and safety assisted driving system, and is of great significance to improve the level of road safety.
8
Wang, Kaili, Jinglei Zhang, and Yida Zhang. "Recognition of Driver Cognitive Distraction Behavior based on Numerical Data." Journal of Scientific and Engineering Research 10, no. 12 (2023): 59–65. https://doi.org/10.5281/zenodo.10466087.
Full textAbstract:
<strong>Abstract </strong>In recent years, with the continuous development of the automotive industry, the number of motor vehicles has also been increasing, which has brought about worrying traffic safety issues. As an important factor in the road traffic system, drivers are a significant factor in causing traffic accidents. Dangerous driving behaviors such as distracted driving and angry driving seriously affect traffic safety. Among them, distracted driving can be divided into different types such as cognitive distracted driving, visual distracted driving, and operational distracted driving. This article mainly focuses on the research of cognitive distracted driving. Due to the certain risks of conducting real vehicle driving experiments, this article uses a driving simulator to simulate driving experiments. The driving state is following driving, and the vehicle operation information data and human factor data of the experimental vehicle are collected. Based on these two types of data, feature extraction is carried out, Establish a driving behavior dataset and establish a recognition model based on optimized GRU, with an accuracy rate of over 80%.
9
Darwish, Karam, and Majd Ali. "Driving Behaviors Recognition Using Deep Neural Networks." Embedded Selforganising Systems 10, no. 5 (2023): 9–12. http://dx.doi.org/10.14464/ess.v10i5.592.
Full textAbstract:
Road accidents are skyrocketing, and traffic safety is a severe problem around the world. Many road traffic deaths are related to drivers’ unsafe behaviors. In this paper, we propose two different deep-learning models which classify the driver’s actions in a 60-second time frame into two main categories: Normal and Aggressive driving based on GPS data collected at 1 Hz, which is later preprocessed and passed to the proposed models to identify dominant driving behavior in each time frame. The models achieved an accuracy of 93.75 percent in real-world tests, which proves the efficiency of this method in driving behavior recognition.
10
Tukaram, Ghodake Sanket, Jadhav Tushar Anil, Pund Mayuri Vishwanath, Pund Raviraj Vishwanath, and Dandekar Pooja Kantilal. "Discriminative Transfer Learning for Driving Pattern Recognition in Unlabeled Scenes." International Journal for Research in Applied Science and Engineering Technology 10, no. 11 (2022): 1925–29. http://dx.doi.org/10.22214/ijraset.2022.47750.
Full textAbstract:
Abstract: Driving behavior has a large impact on behaviour of driver. The lack of a labeled data problem in a driving scene substantially hinders the driving pattern recognition accuracy. However, modeling driving behavior under the dynamic driving conditions is complex, making a quantitative analysis of the the driving behaviour. In this paper, the Driver behaivor dataset was collected from dataset repository. Then, we have to implement the pre-processing techniques. Then, the system is developed the machine learning algorithm such as Random forest and Support Vector Machine algorithm. The experimental results shows that some performance metrics such as accuracy, precision, recall and f1-score. By using the ML is, to classify the Aggressive, normal, slow.
11
Wang, Lili, Wenjie Yao, Chen Chen, and Hailu Yang. "Driving Behavior Recognition Algorithm Combining Attention Mechanism and Lightweight Network." Entropy 24, no. 7 (2022): 984. http://dx.doi.org/10.3390/e24070984.
Full textAbstract:
In actual driving scenes, recognizing and preventing drivers’ non-standard driving behavior is helpful in reducing traffic accidents. To resolve the problems of various driving behaviors, a large range of action, and the low recognition accuracy of traditional detection methods, in this paper, a driving behavior recognition algorithm was proposed that combines an attention mechanism and lightweight network. The attention module was integrated into the YOLOV4 model after improving the feature extraction network, and the structure of the attention module was also improved. According to the 20,000 images of the Kaggle dataset, 10 typical driving behaviors were analyzed, processed, and recognized. The comparison and ablation experimental results showed that the fusion of an improved attention mechanism and lightweight network model had good performance in accuracy, model size, and FLOPs.
12
Ishak, Muhammad Firdaus, Fadhlan Hafizhelmi Kamaru Zaman, Ng Kok Mun, Syahrul Afzal Che Abdullah, and Ahmad Khushairy Makhtar. "Improving night driving behavior recognition with ResNet50." Indonesian Journal of Electrical Engineering and Computer Science 33, no. 3 (2024): 1974. http://dx.doi.org/10.11591/ijeecs.v33.i3.pp1974-1988.
Full textAbstract:
The issue of driving behavior at night poses significant challenges due to reduced visibility and increased risk of accidents. Recent works have leveraged deep learning techniques to enhance night-time driving safety. However, the limited availability of high-quality training data and the lack of robustness in existing models present significant problems. In this work, we propose a novel approach to improve driving behavior recognition at night using ResNet50 with contrast limited adapted histogram equalization (CLAHE). We collected a new dataset and developed a more effective and robust model that can accurately recognize driving behaviors under low-illumination conditions, thereby reducing the likelihood of collisions and improving overall road safety. The experimental results demonstrate significant improvements in the deep learning model’s performance compared to conventional methods. Notably, the ResNet50 model delivers the best performance with accuracy rates of 90.73% using NIGHT-VIS-CLAHE data, demonstrating a 16% improvement in accuracy. For benchmark purposes, the InceptionV3, GoogleNet, and MobileNetV2 models also show enhanced accuracy through CLAHE implementation. Furthermore, NIGHT-VIS-CLAHE implementation in ResNet50 achieved 90.29% accuracy, surpassing the best NIGHT-IR InceptionV3 at 89.27%, highlighting the advantage of ResNet50 with CLAHE in low-light conditions even against infra-red sensor.
13
Ishak, Muhammad Firdaus, Fadhlan Hafizhelmi Kamaru Zaman, Ng Kok Mun, Syahrul Afzal Che Abdullah, and Ahmad Khushairy Makhtar. "Improving night driving behavior recognition with ResNet50." Indonesian Journal of Electrical Engineering and Computer Science 33, no. 3 (2024): 1974–88. https://doi.org/10.11591/ijeecs.v33.i3.pp1974-1988.
Full textAbstract:
The issue of driving behavior at night poses significant challenges due to reduced visibility and increased risk of accidents. Recent works have leveraged deep learning techniques to enhance night-time driving safety. However, the limited availability of high-quality training data and the lack of robustness in existing models present significant problems. In this work, we propose a novel approach to improve driving behavior recognition at night using ResNet50 with contrast limited adapted histogram equalization (CLAHE). We collected a new dataset and developed a more effective and robust model that can accurately recognize driving behaviors under low-illumination conditions, thereby reducing the likelihood of collisions and improving overall road safety. The experimental results demonstrate significant improvements in the deep learning model’s performance compared to conventional methods. Notably, the ResNet50 model delivers the best performance with accuracy rates of 90.73% using NIGHT-VIS-CLAHE data, demonstrating a 16% improvement in accuracy. For benchmark purposes, the InceptionV3, GoogleNet, and MobileNetV2 models also show enhanced accuracy through CLAHE implementation. Furthermore, NIGHT-VIS-CLAHE implementation in ResNet50 achieved 90.29% accuracy, surpassing the best NIGHT-IR InceptionV3 at 89.27%, highlighting the advantage of ResNet50 with CLAHE in low-light conditions even against infra-red sensor.
14
Hou, Junjian, Bingyu Zhang, Yudong Zhong, and Wenbin He. "Research Progress of Dangerous Driving Behavior Recognition Methods Based on Deep Learning." World Electric Vehicle Journal 16, no. 2 (2025): 62. https://doi.org/10.3390/wevj16020062.
Full textAbstract:
In response to the rising frequency of traffic accidents and growing concerns regarding driving safety, the identification and analysis of dangerous driving behaviors have emerged as critical components in enhancing road safety. In this paper, the research progress in the recognition methods of dangerous driving behavior based on deep learning is analyzed. Firstly, the data collection methods are categorized into four types, evaluating their respective advantages, disadvantages, and applicability. While questionnaire surveys provide limited information, they are straightforward to conduct. The vehicle operation data acquisition method, being a non-contact detection, does not interfere with the driver’s activities but is susceptible to environmental factors and individual driving habits, potentially leading to inaccuracies. The recognition method based on dangerous driving behavior can be monitored in real time, though its effectiveness is constrained by lighting conditions. The precision of physiological detection depends on the quality of the equipment. Then, the collected big data are utilized to extract the features related to dangerous driving behavior. The paper mainly classifies the deep learning models employed for dangerous driving behavior recognition into three categories: Deep Belief Network (DBN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). DBN exhibits high flexibility but suffers from relatively slow processing speeds. CNN demonstrates excellent performance in image recognition, yet it may lead to information loss. RNN possesses the capability to process sequential data effectively; however, training these networks is challenging. Finally, this paper concludes with a comprehensive analysis of the application of deep learning-based dangerous driving behavior recognition methods, along with an in-depth exploration of their future development trends. As computer technology continues to advance, deep learning is progressively replacing fuzzy logic and traditional machine learning approaches as the primary tool for identifying dangerous driving behaviors.
15
Chen, Shengdi, Qingwen Xue, Xiaochen Zhao, Yingying Xing, and Jian John Lu. "Risky Driving Behavior Recognition Based on Vehicle Trajectory." International Journal of Environmental Research and Public Health 18, no. 23 (2021): 12373. http://dx.doi.org/10.3390/ijerph182312373.
Full textAbstract:
This paper proposes a measurement of risk (MOR) method to recognize risky driving behavior based on the trajectory data extracted from surveillance videos. Three types of risky driving behavior are studied in this paper, i.e., speed-unstable driving, serpentine driving, and risky car-following driving. The risky driving behavior recognition model contains an MOR-based risk evaluation model and an MOR threshold selection method. An MOR-based risk evaluation model is established for three types of risky driving behavior based on driving features to quantify collision risk. Then, we propose two methods, i.e., the distribution-based method and the boxplot-based method, to determine the threshold value of the MOR to recognize risky driving behavior. Finally, the trajectory data extracted from UAV videos are used to validate the proposed model. The impact of vehicle types is also taken into consideration in the model. The results show that there are significant differences between threshold values for cars and heavy trucks when performing speed-unstable driving and risky car-following driving. In addition, the difference between the proportion of recognized risky driving behavior in the testing dataset compared with that in the training dataset is limited to less than 3.5%. The recognition accuracy of risky driving behavior with the boxplot- and distribution-based methods are, respectively, 91% and 86%, indicating the validation of the proposed model. The proposed model can be widely applied to risky driving behavior recognition in video-based surveillance systems.
16
Li, Min, Wuhong Wang, Zhen Liu, Mingjun Qiu, and Dayi Qu. "Driver Behavior and Intention Recognition Based on Wavelet Denoising and Bayesian Theory." Sustainability 14, no. 11 (2022): 6901. http://dx.doi.org/10.3390/su14116901.
Full textAbstract:
Driver behavior and intention recognition affects traffic safety. Many scholars use the steering wheel angle, distance of the brake pedal, distance of the accelerator pedal, and turn signal as input data to identify driver behaviors and intentions. However, in terms of time, the acquisition of these parameters has a relative delay, which lengthens the identification time. Therefore, this study uses drivers’ EEG (electroencephalograph) data as input parameters to identify driver behaviors and intentions. The key to the driving intention recognition of EEG signals is to reduce their noise. Noise interference has a significant influence on EEG driving intention recognition. To substantially denoise EEG signals, this study selects wavelet transform theory and wavelet packet transform technology, collects the EEG signals during driving, uses the threshold noise reduction method on EEG signals to reduce noise, and achieves noise reduction through wavelet packet reconstruction. After the wavelet packet coefficients of EEG signals are obtained, the energy characteristics of the wavelet packet coefficients are extracted as input to the Bayesian theoretical model for driver behavior and intention recognition. Results show that the maximum recognition rate of the Bayesian theoretical model reaches 82.6%. Early driver behavior and intention recognition has important research significance for traffic safety and sustainable traffic development.
17
bin Jamal Mohd Lokman, Eilham Hakimie, Vik Tor Goh, Timothy Tzen Vun Yap, and Hu Ng. "Driving style recognition using machine learning and smartphones." F1000Research 11 (January 18, 2022): 57. http://dx.doi.org/10.12688/f1000research.73134.1.
Full textAbstract:
Background: The lack of real-time monitoring is one of the reasons for the lack of awareness among drivers of their dangerous driving behavior. This work aims to develop a driver profiling system where a smartphone’s built-in sensors are used alongside machine learning algorithms to classify different driving behaviors. Methods: We attempt to determine the optimal combination of smartphone sensors such as accelerometer, gyroscope, and GPS in order to develop an accurate machine learning algorithm capable of identifying different driving events (e.g. turning, accelerating, or braking). Results: In our preliminary studies, we encountered some difficulties in obtaining consistent driving events, which had the potential to add “noise” to the observations, thus reducing the accuracy of the classification. However, after some pre-processing, which included manual elimination of extraneous and erroneous events, and with the use of the Convolutional Neural Networks (CNN), we have been able to distinguish different driving events with an accuracy of about 95%. Conclusions: Based on the results of preliminary studies, we have determined that proposed approach is effective in classifying different driving events, which in turn will allow us to determine driver’s driving behavior.
18
bin Jamal Mohd Lokman, Eilham Hakimie, Vik Tor Goh, Timothy Tzen Vun Yap, and Hu Ng. "Driving event recognition using machine learning and smartphones." F1000Research 11 (December 19, 2022): 57. http://dx.doi.org/10.12688/f1000research.73134.2.
Full textAbstract:
Background: The lack of real-time monitoring is one of the reasons for the lack of awareness among drivers of their dangerous driving behavior. This work aims to develop a driver profiling system where a smartphone’s built-in sensors are used alongside machine learning algorithms to classify different driving behaviors. Methods: We attempt to determine the optimal combination of smartphone sensors such as accelerometer, gyroscope, and GPS in order to develop an accurate machine learning algorithm capable of identifying different driving events (e.g. turning, accelerating, or braking). Results: In our preliminary studies, we encountered some difficulties in obtaining consistent driving events, which had the potential to add “noise” to the observations, thus reducing the accuracy of the classification. However, after some pre-processing, which included manual elimination of extraneous and erroneous events, and with the use of the Convolutional Neural Networks (CNN), we have been able to distinguish different driving events with an accuracy of about 95%. Conclusions: Based on the results of preliminary studies, we have determined that the proposed approach is effective in classifying different driving events, which in turn will allow us to determine driver’s driving behavior.
19
Zhang, Siyang, Zherui Zhang, and Chi Zhao. "A Method of Intelligent Driving-Style Recognition Using Natural Driving Data." Applied Sciences 14, no. 22 (2024): 10601. http://dx.doi.org/10.3390/app142210601.
Full textAbstract:
At present, achieving efficient, sustainable, and safe transportation has led to increasing attention on driving behavior recognition and advancements in autonomous driving. Identifying diverse driving styles and corresponding types is crucial for providing targeted training and assistance to drivers, enhancing safety awareness, optimizing driving costs, and improving autonomous driving systems responses. However, current studies mainly focus on specific driving scenarios, such as free driving, car-following, and lane-changing, lacking a comprehensive and systematic framework to identify the diverse driving styles. This study proposes a novel, data-driven approach to driving-style recognition utilizing naturalistic driving data NGSIM. Specifically, the NGSIM dataset is employed to categorize car-following and lane-changing groups according to driving-state extraction conditions. Then, characteristic parameters that fully represent driving styles are optimized through correlation analysis and principal component analysis for dimensionality reduction. The K-means clustering algorithm is applied to categorize the car-following and lane-changing groups into three driving styles: conservative, moderate, and radical. Based on the clustering results, a comprehensive evaluation of the driving styles is conducted. Finally, a comparative evaluation of SVM, Random Forest, and KNN recognition indicates the superiority of the SVM algorithm and highlights the effectiveness of dimensionality reduction in optimizing characteristic parameters. The proposed method achieves over 97% accuracy in identifying car-following and lane-changing behaviors, confirming that the approach based on naturalistic driving data can effectively and intelligently recognize driving styles.
20
Li, Pengfei, Jianjun Shi, and Xiaoming Liu. "Driving Style Recognition Based on Driver Behavior Questionnaire." Open Journal of Applied Sciences 07, no. 04 (2017): 115–28. http://dx.doi.org/10.4236/ojapps.2017.74010.
Full text
21
Yan, Chao, Frans Coenen, Yong Yue, Xiaosong Yang, and Bailing Zhang. "Video-Based Classification of Driving Behavior Using a Hierarchical Classification System with Multiple Features." International Journal of Pattern Recognition and Artificial Intelligence 30, no. 05 (2016): 1650010. http://dx.doi.org/10.1142/s0218001416500105.
Full textAbstract:
Driver fatigue and inattention have long been recognized as one of the main contributing factors in traffic accidents. Therefore, the development of intelligent driver assistance systems, which provides automatic monitoring of driver's vigilance, is an urgent and challenging task. This paper presents a novel system for video-based driving behavior recognition. The fundamental idea is to monitor driver's hand movements and to use these as predictors for safe/unsafe driving behavior. In comparison to previous work, the proposed method utilizes hierarchical classification and treats driving behavior in terms of a spatio-temporal reference framework as opposed to a static image. The approach was verified using the Southeast University Driving-Posture Dataset, a dataset comprised of video clips covering aspects of driving such as: normal driving, responding to a cell phone call, eating and smoking. After pre-processing for illumination variations and motion sequence segmentation, eight classes of behavior were identified. The overall prediction accuracy obtained using the proposed approach was [Formula: see text] when using a hierarchical classification approach. The proposed approach was able to clearly identify two dangerous driving behaviors, Responding to a cellphone call and Eating, with recognition rates of 92.39% and 92.29% respectively.
22
Gaikwad, Aryan. "COGNITIVE DRIVER ACTION RECOGNITION." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 04 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem30954.
Full textAbstract:
Operating an automobile is a multifaceted endeavor, demanding unwavering focus and attention from the driver. Distracted driving, encompassing any behavior that diverts the driver's concentration away from the road, poses a grave threat to road safety. Alarming statistics reveal that approximately 1.35 million lives are tragically lost each year due to road traffic accidents, inflicting significant economic ramifications, with road traffic crashes costing most nations an estimated 3% of their gross domestic product. The primary objective of our project is to put in place an exhaustive process for identifying potentially dangerous driving behaviors and discerning appropriate driving practices in light of this disappointing reality. By utilizing a wide range of machine learning models, we aim to correctly classify the given photos into discrete groups that correlate to various types of driver distraction. Furthermore, our work goes beyond simple classification; it also aims to perform a comparison analysis of different Machine Learning Models in order to determine how well they perform and how accurate they are in the context of cognitive driver action detection. This all-encompassing strategy demonstrates our dedication to improving traffic safety and lowering the possibility of collisions and injuries to other drivers. Key Words: Transfer learning, Deep learning, Image classification, Distracted driving, TensorFlow.
23
Sun, Yifan, Jinglei Zhang, Xiaoyuan Wang, Zhangu Wang, and Jie Yu. "Recognition Method of Drinking-driving Behaviors Based on PCA and RBF Neural Network." PROMET - Traffic&Transportation 30, no. 4 (2018): 407–17. http://dx.doi.org/10.7307/ptt.v30i4.2657.
Full textAbstract:
Drinking-driving behaviors are important causes of road traffic injuries, which are serious threats to the lives and property of traffic participants. Therefore, reducing the occurrences of drinking-driving behaviors has become an important problem of traffic safety research. Forty-eight male drivers and six female drivers who could drink moderate alcohol were chosen as participants. The drivers’ physiological data, operation behavior data, car running data, and driving environment data were collected by designing various virtual traffic scenes and organizing drivers to conduct driving simulation experiments. The original variables were analyzed by the Principal Component Analysis (PCA), and seven principal components were extracted as the input vector of the Radial Basis Function (RBF) neural network. The principal component data was used to train and verify the RBF neural network. The Levenberg-Marquardt (LM) algorithm was chosen to train the parameters of the neural network and build a drinking-driving recognition model based on PCA and RBF neural network to realize an accurate recognition of drinking-driving behaviors. The test results showed that the drinking-driving recognition model based on PCA and RBF neural network could identify drinking drivers accurately during driving process with a recognition accuracy of 92.01%, and the operation efficiency of the model was high. The research can provide useful reference for prevention and treatment of drinking and driving and traffic safety maintenance.
24
Jeon, Jae Hyeon, Mi Kyeong Jeong, and Mee Sun Choi. "A Study on Risky Driving Behaviors and Perceptions of Delivery Motorcycle Drivers." Forum of Public Safety and Culture 43 (June 30, 2025): 123–37. https://doi.org/10.52902/kjsc.2025.43.123.
Full textAbstract:
This study aims to analyze the types and characteristics of risky driving behavior among delivery motorcycle drivers, who have become a growing concern in terms of traffic safety hazards. To identify the various patterns of such risky driving behavior, field observations and video recordings were conducted in areas with a high incidence of motorcycle traffic accidents and dense delivery motorcycle activity. First, the study identified the primary time periods during which delivery motorcycles operate and categorized the risky driving behaviors in detail. It then analyzed the proportion of each behavior type to determine the most prevalent risky driving behaviors. The analysis revealed ten major types of risky driving behavior among delivery motorcycle drivers. In addition to serious traffic offences such as speeding, signal violations, and crossing the centerline, other behaviors include cutting to the front of waiting vehicles at intersections, changing lanes while passing through intersections, creating and using unauthorized paths through intersections, riding on sidewalks, crossing at pedestrian crosswalks, lane violations, and designated lane violations. The newly identified behavior types represent driving practices that exploit the small body size of motorcycles. These behaviors were found to occur more frequently during traffic congestion. Furthermore, a survey targeting delivery motorcycle drivers was carried out to analyze their perception of each type of risky driving behavior—whether they recognized it as a traffic offence, regarded it as dangerous, and how often they engaged in it. The average recognition rate of these behaviors as traffic offences was 91.5%, indicating a high level of awareness. However, the recognition rates for designated lane violations and cutting to the front of waiting vehicles at intersections were relatively low, and these behaviors were also frequently committed. Although all ten types of risky driving behavior were perceived as dangerous, drivers tended to violate them even when aware of the risks. The results of this study, which identified major types of risky driving behavior among delivery motorcycle drivers and analyzed their perceptions of these behaviors, are expected to serve as a foundation for developing safety management measures—such as targeted education and enforcement strategies—specifically tailored for delivery motorcycle drivers in the future.
25
Xiao, Weichu, Hongli Liu, Ziji Ma, Weihong Chen, Changliang Sun, and Bo Shi. "Fatigue Driving Recognition Method Based on Multi-Scale Facial Landmark Detector." Electronics 11, no. 24 (2022): 4103. http://dx.doi.org/10.3390/electronics11244103.
Full textAbstract:
Fatigue driving behavior recognition in all-weather real driving environments is a challenging task. Accurate recognition of fatigue driving behavior is helpful to improve traffic safety. The facial landmark detector is crucial to fatigue driving recognition. However, existing facial landmark detectors are mainly aimed at stable front face color images instead of side face gray images, which is difficult to adapt to the fatigue driving behavior recognition in real dynamic scenes. To maximize the driver’s facial feature information and temporal characteristics, a fatigue driving behavior recognition method based on a multi-scale facial landmark detector (MSFLD) is proposed. First, a spatial pyramid pooling and multi-scale feature output (SPP-MSFO) detection model is built to obtain a face region image. The MSFLD is a lightweight facial landmark detector, which is composed of convolution layers, inverted bottleneck blocks, and multi-scale full connection layers to achieve accurate detection of 23 key points on the face. Second, the aspect ratios of the left eye, right eye and mouth are calculated in accordance with the coordinates of the key points to form a fatigue parameter matrix. Finally, the combination of adaptive threshold and statistical threshold is used to avoid misjudgment of fatigue driving recognition. The adaptive threshold is dynamic, which solves the problem of the difference in the aspect ratio of the eyes and mouths of different drivers. The statistical threshold is a supplement to solve the problem of driver’s low eye threshold and high mouth threshold. The proposed methods are evaluated on the Hunan University Fatigue Detection (HNUFDD) dataset. The proposed MSFLD achieves a normalized mean error value of 5.4518%, and the accuracy of the fatigue driving recognition method based on MSFLD achieves 99.1329%, which outperforms that of state-of-the-art methods.
26
Melnyk, Yurii, Serhii Otrokh, Oleksandr Sarafannikov, and Yurii Lebid. "Driver Behavior Recognition Based on Neural Networks Theory." Electronics and Control Systems 1, no. 75 (2023): 44–48. http://dx.doi.org/10.18372/1990-5548.75.17554.
Full textAbstract:
The article deals with the problem of driver behavior while driving the vehicle. Driver distraction can lead to serious accidents that threaten human life and public property around the world. Solving the problem of preventing dangerous driving behavior will reduce the risk of getting into an accident in the future. Thus, there is a need for a smart vehicle that will support driver behavior recognition functionality. A possible solution to the problem using an artificial neural network for automatic recognition of driver behavior on a real set of driver behavior data is considered. The high accuracy and efficiency of the developed model recognition is obtained.
27
Sun, Lishan, Liya Yao, Jian Rong, Jinyan Lu, Bohua Liu, and Shuwei Wang. "Simulation Analysis on Driving Behavior during Traffic Sign Recognition." International Journal of Computational Intelligence Systems 4, no. 3 (2011): 353. http://dx.doi.org/10.2991/ijcis.2011.4.3.9.
Full text
28
Yuan, Yasheng, Fengzhi Dai, Di Yin, and Yuxuan Zhu. "Research on Bad Driving Detection Based on Behavior Recognition." Proceedings of International Conference on Artificial Life and Robotics 26 (January 21, 2021): 630–34. http://dx.doi.org/10.5954/icarob.2021.os13-11.
Full text
29
Chu Jinghui, 褚晶辉, 张姗 Zhang Shan, 汤文豪 Tang Wenhao, and 吕卫 Lü Wei. "Driving Behavior Recognition Method Based on Tutor-Student Network." Laser & Optoelectronics Progress 57, no. 6 (2020): 061019. http://dx.doi.org/10.3788/lop57.061019.
Full text
30
Sun, Lishan, Liya Yao, Jian Rong, Jinyan Lu, Bohua Liu, and Shuwei Wang. "Simulation Analysis on Driving Behavior during Traffic Sign Recognition." International Journal of Computational Intelligence Systems 4, no. 3 (2011): 353–60. http://dx.doi.org/10.1080/18756891.2011.9727793.
Full text
31
Chen, Depeng, Zhijun Chen, Yishi Zhang, Xu Qu, Mingyang Zhang, and Chaozhong Wu. "Driving Style Recognition under Connected Circumstance Using a Supervised Hierarchical Bayesian Model." Journal of Advanced Transportation 2021 (June 2, 2021): 1–12. http://dx.doi.org/10.1155/2021/6687378.
Full textAbstract:
In recent years, the automated driving system has been known to be one of the most popular research topics of artificial intelligence (AI) and intelligent transportation system (ITS). The journey experience on automated vehicles and the intelligent automated driving system could be improved by individualization driving understanding. Although previous studies have proposed methods for driving styles understanding, the individualization driving classification has not been addressed thoroughly. Therefore, in this study, a supervised method is proposed to understand driving behavioral structure and the latent driving styles by incorporating the prior knowledge. Firstly, a novel method is established for driving behavioral encoding and raw driving data mining. Then, the Labeled Latent Dirichlet Allocation (LLDA) is proposed to understand the latent driving styles from individual driving with driving behaviors. Finally, the Safety Pilot Model Deployment (SPMD) data are used to validate the performance of the proposed model. Experimental results show that the proposed model uncovers latent driving styles effectively and shows good agreement to real situations, which provides theoretical guidance on driving behavior recognition for better individual experience on automated driving vehicles.
32
Al-qaysi, Ziadoon. "Taxonomy, Open Challenges, Motivations, and Recommendations in Driver Behavior Recognition: A Systematic Review." Iraqi Journal For Computer Science and Mathematics 5, no. 3 (2024): 358–77. http://dx.doi.org/10.52866/ijcsm.2024.05.03.021.
Full textAbstract:
Driver behavior has a major role in many of the unpleasant things that happen when driving, such ascrashes or accidents, heavy traffic, abrupt braking, and acceleration and deceleration. Numerous investigationshave been carried out to look into the variables influencing driving behavior. To offer a thorough analysis andclassify these findings according to a logical classification, further research is required. The goal of this systematicreview is to enhance knowledge about the variables influencing driving behavior. A taxonomy on the subject ofdriver behavior in various ITS domains and their categories was also produced by this work.A systematic review of the literature was performed in accordance with PRISMA (Preferred Reporting Items forSystematic Reviews and Meta-Analyses) guidelines to gain insight into driver behaviour recognition.Specifically, IEEE Explore, ScienceDirect and Springer databases were searched to identify any relevant articleswith a focus on "driver behavior," "driver style," "driver pattern," "driver simulator," and "visual attention,” from2008 to 2021 (15 April).Several filtering and scanning procedures were performed on all 606 retrieved articles in compliance with theexclusion/inclusion criteria; nonetheless, only 50 articles met the requirements. The criteria-compliant referenceswere examined and evaluated. Furthermore, every piece that was included was classified using a taxonomy. Thefour categories created by the taxonomy are review, experiment, framework, and other study types. To illustratethe main gaps in the literature regarding the identification of driving behavior, a discussion and analysis werepresented. This thorough analysis has highlighted the issues and reasons while also pointing forth fresh researchdirections.
33
Abhishek Dixit. "Trajectory Data Driven Driving Style Recognition for Autonomous Vehicles Using Unsupervised Clustering." Communications on Applied Nonlinear Analysis 31, no. 6s (2024): 715–23. http://dx.doi.org/10.52783/cana.v31.1314.
Full textAbstract:
Introduction: This research focuses on enhancing the understanding and classification of vehicle driving styles by analyzing extensive trajectory data. Recognizing and categorizing different driving behaviours is crucial, particularly for the development of autonomous vehicles, which must predict and respond to the diverse actions of human drivers. Understanding these driving styles is essential for improving road safety and ensuring that autonomous systems can navigate mixed traffic environments effectively. Objectives: The primary objective of this study is to classify vehicle driving styles into distinct categories like aggressive, moderate, and traditional by leveraging unsupervised learning techniques. This classification aims to improve the predictive capabilities of autonomous vehicles and enhance overall road safety by providing a more nuanced understanding of driving behaviours. Methods: The study begins by applying Principal Component Analysis (PCA) to simplify complex trajectory data, reducing multiple characteristic indexes into two principal components that encapsulate the most significant features related to driving behaviour. To determine the optimal number of driving style categories, the "Elbow rule" and Silhouette analysis are employed, followed by the application of the K-means clustering algorithm. This approach allows for the effective grouping of driving styles based on the processed data. Results: The analysis identified three distinct driving styles: aggressive, moderate, and traditional. Aggressive driving is characterized by higher velocities, greater acceleration, and increased jerk, along with shorter space and time headways. Traditional driving styles exhibit more conservative behaviours, with lower speeds, reduced acceleration, and greater following distances. Moderate driving styles lie between these two extremes, reflecting a balanced approach in terms of speed, acceleration, and headway distances. Conclusions: The findings of this study have significant implications for the development and operation of autonomous vehicles. By accurately classifying driving styles, autonomous systems can better anticipate and react to the behavior of surrounding vehicles, thereby enhancing safety in mixed traffic environments. The research also demonstrates the potential for extending the proposed unsupervised learning approach to other driving scenarios and datasets, offering a scalable solution for ongoing advancements in intelligent transportation systems.
34
Lu, Yu Feng, and Chun Ling Li. "Recognition of Driver Turn Behavior Based on Video Analysis." Advanced Materials Research 433-440 (January 2012): 6230–34. http://dx.doi.org/10.4028/www.scientific.net/amr.433-440.6230.
Full textAbstract:
In view of the shortcoming of driver state detection system which may take turn behavior as driver distraction, a new method to recognize turn behavior was proposed based on video images analysis. The driver hands position in different driving behavior were analyzed and we found that the position of driver’s hands changed more violent when in turning than in other driving behavior. So we may use standard deviation of driver hands position to recognize driver turn behavior. In order to improve the hands locating speed the Particle Filtering was used to track the driver hands. And experiments resulted that the recognition algorithm can identify the driver's turn behavior.
35
Pan, Yong, Xiangmo Zhao, Zhigang Xu, Junwei Li, Yifei Li, and Li Liu. "Research on Abnormal Behavior Recognition of Buses Based on Improved Support Vector Machine." Journal of Advanced Transportation 2021 (July 26, 2021): 1–8. http://dx.doi.org/10.1155/2021/2020882.
Full textAbstract:
The abnormal driving behavior of buses brings about greater security threat. How to effectively identify the abnormal driving behavior of buses has become one of the problems of cracking public transportation safety. This paper constructs an abnormal behavior recognition model of buses based on improved support vector machine. Through the verification, the model has a high recognition rate, which provides an important means for further improving the safety of public transportation operations.
36
Liu, Shijie, Xiaoyuan Wang, Chenglin Bai, et al. "Recognition Method of Vehicle Cluster Situation Based on Set Pair Logic considering Driver’s Cognition." Computational Intelligence and Neuroscience 2021 (September 4, 2021): 1–15. http://dx.doi.org/10.1155/2021/9809279.
Full textAbstract:
The recognition of vehicle cluster situations is one of the critical technologies of advanced driving, such as intelligent driving and automated driving. The accurate recognition of vehicle cluster situations is helpful for behavior decision-making safe and efficient. In order to accurately and objectively identify the vehicle cluster situation, a vehicle cluster situation model is proposed based on the interval number of set pair logic. The proposed model can express the traffic environment’s knowledge considering each vehicle’s characteristics, grouping relationships, and traffic flow characteristics in the target vehicle’s interest region. A recognition method of vehicle cluster situation is designed to infer the traffic environment and driving conditions based on the connection number of set pair logic. In the proposed model, the uncertainty of the driver’s cognition is fully considered. In the recognition method, the relative uncertainty and relative certainty of driver’s cognition, traffic information, and vehicle cluster situation are fully considered. The verification results show that the proposed recognition method of vehicle cluster situations can realize accurate and objective recognition. The proposed anthropomorphic recognition method could provide a basis for vehicle autonomous behavior decision-making.
37
Hao, Zhanjun, Zepei Li, Xiaochao Dang, Zhongyu Ma, and Gaoyuan Liu. "MM-LMF: A Low-Rank Multimodal Fusion Dangerous Driving Behavior Recognition Method Based on FMCW Signals." Electronics 11, no. 22 (2022): 3800. http://dx.doi.org/10.3390/electronics11223800.
Full textAbstract:
Multimodal research is an emerging field of artificial intelligence, and the analysis of dangerous driving behavior is one of the main application scenarios in the field of multimodal fusion. Aiming at the problem of data heterogeneity in the process of behavior classification by multimodal fusion, this paper proposes a low-rank multimodal data fusion method, which utilizes the complementarity between data modalities of different dimensions in order to classify and identify dangerous driving behaviors. This method uses tensor difference matrix data to force low-rank fusion representation, improves the verification efficiency of dangerous driving behaviors through multi-level abstract tensor representation, and solves the problem of output data complexity. A recurrent network based on the attention mechanism, AR-GRU, updates the network input parameter state and learns the weight parameters through its gated structure. This model improves the dynamic connection between modalities on heterogeneous threads and reduces computational complexity. Under low-rank conditions, it can quickly and accurately classify and identify dangerous driving behaviors and give early warnings. Through a large number of experiments, the accuracy of this method is improved by an average of 1.76% compared with the BiLSTM method and the BiGRU-IAAN method in the training and verification of the self-built dataset.
38
Pingo, Alberto, João Castro, Paulo Loureiro, et al. "Driving Behavior Classification Using a ConvLSTM." Future Transportation 5, no. 2 (2025): 52. https://doi.org/10.3390/futuretransp5020052.
Full textAbstract:
This work explores the classification of driving behaviors using a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks (ConvLSTM). Sensor data are collected from a smartphone application and undergo a preprocessing pipeline, including data normalization, labeling, and feature extraction, to enhance the model’s performance. By capturing temporal and spatial dependencies within driving patterns, the proposed ConvLSTM model effectively differentiates between normal and aggressive driving behaviors. The model is trained and evaluated against traditional stacked LSTM and Bidirectional LSTM (BiLSTM) architectures, demonstrating superior accuracy and robustness. Experimental results confirm that the preprocessing techniques improve classification performance, ensuring high reliability in driving behavior recognition. The novelty of this work lies in a simple data preprocessing methodology combined with the specific application scenario. By enhancing data quality before feeding it into the AI model, we improve classification accuracy and robustness. The proposed framework not only optimizes model performance but also demonstrates practical feasibility, making it a strong candidate for real-world deployment.
39
Lin, Yingcheng, Dingxin Cao, Zanhao Fu, Yanmei Huang, and Yanyi Song. "A Lightweight Attention-Based Network towards Distracted Driving Behavior Recognition." Applied Sciences 12, no. 9 (2022): 4191. http://dx.doi.org/10.3390/app12094191.
Full textAbstract:
Distracted driving is currently a global issue causing fatal traffic crashes and injuries. Although deep learning has achieved significant success in various fields, it still faces the trade-off between computation cost and overall accuracy in the field of distracted driving behavior recognition. This paper addresses this problem and proposes a novel lightweight attention-based (LWANet) network for image classification tasks. To reduce the computation cost and trainable parameters, we replace standard convolution layers with depthwise separable convolutions and optimize the classic VGG16 architecture by 98.16% trainable parameters reduction. Inspired by the attention mechanism in cognitive science, a lightweight inverted residual attention module (IRAM) is proposed to simulate human attention, extract more specific features, and improve the overall accuracy. LWANet achieved an accuracy of 99.37% on Statefarm’s dataset and 98.45% on American University in Cairo’s dataset. With only 1.22 M trainable parameters and a model file size of 4.68 MB, the quantitative experimental results demonstrate that the proposed LWANet obtains state-of-the-art overall performance in deep learning-based distracted driving behavior recognition.
40
Yang, Jinhao, Junwen Cao, and Mingyu Fang. "Personalized trajectory inference framework integrating driving behavior recognition and temporal dependency learning." PLOS One 20, no. 7 (2025): e0326937. https://doi.org/10.1371/journal.pone.0326937.
Full textAbstract:
This study proposes a Driving style-Tri Channel Trajectory Model (DS-TCTM) to enhance vehicle trajectory prediction accuracy and driving safety. The framework operates through three rigorously designed stages: (1)Data preprocessing involving kinematics feature extraction, (2)Driving style recognition utilizing acceleration variation rate and average time headway combined with K-Means++ traffic density clustering and K-neighbor Gaussian mixture model (K-GMM) analysis to classify driving behaviors into conservative, moderate, and radical categories, and (3)Personalized trajectory prediction employing a multi-level neural architecture with dedicated sub-networks for distinct driving styles. Experimental evaluations demonstrate DS-TCTM’s superior performance across multiple dimensions. The model achieves a mean RMSE of 4.46 and NLL of 3.89 across varying prediction horizons, with 35.8% error reduction attained after 100 hyperparameter optimization iterations. Comparative analysis with baseline models (LSTM, Social-LSTM, Social-Velocity-LSTM, Convolutional-Social-LSTM) reveals particularly enhanced accuracy in long-term predictions. These results confirm DS-TCTM’s effectiveness in capturing driving style impacts on trajectory patterns, providing reliable prediction enhancements for vehicle safety systems. This methodology advances personalized trajectory modeling with practical intelligent transportation applications.
41
Kadar, Jimmy Abdel, Margareta Aprilia Kusuma Dewi, Endang Suryawati, et al. "Distracted driver behavior recognition using modified capsule networks." Journal of Mechatronics, Electrical Power, and Vehicular Technology 14, no. 2 (2023): 177–85. http://dx.doi.org/10.14203/j.mev.2023.v14.177-185.
Full textAbstract:
Human activity recognition (HAR) is an increasingly active study field within the computer vision community. In HAR, driver behavior can be detected to ensure safe travel. Detect driver behaviors using a capsule network with leave-one-subject-out validation. The study was done using CapsNet with leave-one-subject-out validation to identify driving habits. The proposed method in this study consists of two parts, namely encoder and decoder. The encoder used in this study modifies Sabour’s capsule network architecture by adding a convolution layer before going to the primary capsule layer. The proposed method is evaluated using a primary dataset with 10 classes and 300 images for each class. The dataset is split based on hold-out validation and leave-one-subject-out validation. The resulting models were then compared to conventional CNN architecture. The objective of the research is to identify driving behavior. In this study, the proposed method results an accuracy rate of 97.83 % in the split dataset using hold-out validation. However, the accuracy decreased by 53.11 % when the proposed method was used on a split dataset using leave-one-subject-out validation. This is because the proposed method extracts all features including the attributes of each participant contained in the input image (user-independent). Thus, the resulting model in this study tends to overfit.
42
Li, Jiajun. "Data-driven Identification and Behavioral Assessment of Anxious Drivers Based on Fuzzy Analytic Hierarchy Processes." Academic Journal of Science and Technology 8, no. 3 (2023): 39–46. http://dx.doi.org/10.54097/na04hd53.
Full textAbstract:
A significant aspect of enhancing road safety is the understanding and recognition of anxious driving behavior. In this paper, we present a comprehensive approach to identifying and assessing anxious drivers by leveraging factor analytical techniques and fuzzy Analytic Hierarchy Processes (FAHP) based on the effective responses from the Driving Behavior Survey (DBS). The factor analysis results indicate that anxious driving behavior is a multi-dimensional construct, comprising multiple key factors such as aggressiveness, distraction, exaggerated caution and driving performance deficits. These dimensions are intricately interconnected and collectively contribute to the overall assessment of a driver's anxious behavior. By utilizing the weights determined through the implementation of the FAHP method on the factor structure, the anxiety ratings for individual drivers generated from our data-driven approach provide invaluable information for various stakeholders, including traffic safety authorities, insurance companies, and drivers themselves.
43
Zhu, Shengxue, Chongyi Li, Kexin Fang, Yichuan Peng, Yuming Jiang, and Yajie Zou. "An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data." Electronics 11, no. 10 (2022): 1557. http://dx.doi.org/10.3390/electronics11101557.
Full textAbstract:
It is of great significance to identify dangerous driving behavior by extracting vehicle trajectory through video monitoring to ensure highway traffic safety. At present, there is no suitable method to identify dangerous driving vehicles accurately based on trajectory data. This paper aims to develop a detection algorithm for identifying dangerous driving behavior based on the road scene, which is mainly composed of imbalanced dangerous driver detection and labeling, extraction of driving behavior characteristics and the establishment of a recognition model about dangerous driving behavior. Firstly, this paper defines the risk index of the vehicle related to five types of dangerous driving behavior: dangerous following, lateral deviation, frequent acceleration and deceleration, frequent lane change, and forced insertion. Then, a variety of methods, including K-means clustering, local factor anomaly algorithm, isolation forest and OneClassSVM, are used to carry out anomaly detection on the risk indicators of drivers, and the optimal method is proposed to identify dangerous drivers. Then, the speed and acceleration of each vehicle are Fourier transformed to obtain the characteristics of the driver’s driving behavior. Finally, considering the imbalanced characteristic of the analyzed dataset with a very small proportion of dangerous drivers, this paper compares a variety of imbalanced classification algorithms to optimize the recognition performance of dangerous driving behavior. The results show that the OneClassSVM detection algorithm can be effectively applied to the identification of dangerous driving behavior. The improved Xgboost algorithm performs best for the extremely imbalanced data of dangerous drivers.
44
Xue, Honghao. "New perspective on human-computer interaction-based on speech recognition in driving." Applied and Computational Engineering 31, no. 1 (2024): 78–85. http://dx.doi.org/10.54254/2755-2721/31/20230125.
Full textAbstract:
With the popularity of smart driving and in-vehicle intelligent systems, speech recognition plays an important role in driving as a key link of human-computer interaction. However, although speech recognition systems have been widely used, their application inhuman-computer interaction still needs to be improved. The purpose of this paper is to examine or review the latest perspectives on speech recognition as part of human-computer interaction in driving. lt provides an in-depth understanding of the potential and future development of speech recognition in driving by exploring, among other things, new directions and features that can be improved. Through a comprehensive analysis of relevant literature and research results, this paper will provide an overview of the current state of speech recognition in human-computer interaction, point out the challenges and limitations that still exist in the driving environment, and focus on new perspectives on speech recognition in driving that may enable more highly accurate command recognition and natural conversational interaction to enhance the driving experience and safety through the use of advanced speech recognition technologies. Explore how technologies such as artificial intelligence and machine learning can be used to drive the development of speech recognition and address current challenges. ln addition, research advances in the areas of driving behavior analysis, emotion recognition, and personalized driving related to speech recognition will be explored. The review and analysis in this paper will provide valuable references and guidance for further research and development of speech recognition-based driving human-computer interaction systems.
45
Liu, Long, Zhelong Wang, and Sen Qiu. "Driving Behavior Tracking and Recognition Based on Multisensors Data Fusion." IEEE Sensors Journal 20, no. 18 (2020): 10811–23. http://dx.doi.org/10.1109/jsen.2020.2995401.
Full text
46
Martinelli, Fabio, Francesco Mercaldo, Albina Orlando, Vittoria Nardone, Antonella Santone, and Arun Kumar Sangaiah. "Human behavior characterization for driving style recognition in vehicle system." Computers & Electrical Engineering 83 (May 2020): 102504. http://dx.doi.org/10.1016/j.compeleceng.2017.12.050.
Full text
47
Zhao, Lei, Ting Xu, Zhishun Zhang, and Yanjun Hao. "Lane-Changing Recognition of Urban Expressway Exit Using Natural Driving Data." Applied Sciences 12, no. 19 (2022): 9762. http://dx.doi.org/10.3390/app12199762.
Full textAbstract:
The traffic environment at the exit of the urban expressway is complex, and vehicle lane-changing behavior occurs frequently, making it prone to traffic conflict and congestion. To study the traffic conditions at the exit of the urban expressway and improve the road operation capacity, this paper analyzes the characteristics of lane-changing behaviors at the exit, adds driving style into the influencing factors of lane-changing, and recognizes one’s lane-changing intention based on driving data. A UAV (unmanned aerial vehicle) is used to collect the natural driving track data of the urban expressway diverge area, the track segments of vehicle lane-changing that meet the standards are extracted, and 374 lane-changing segments are obtained. K-means++ is used to cluster the driving style of the lane-changing segments which is grouped into three clusters, corresponding to “ordinary”, “radical”, and “conservative”. Through the random forest model used to identify and predict driving style, the accuracy reaches 93%. Considering the characteristics of a single time point and the characteristics of the historical time window, XGBoost, LightGBM, and the Stacking fusion model are established to recognize one’s lane-changing intention. The results show that the models can well recognize the lane-changing intention of drivers. The Stacking fusion model has the highest accuracy, while the LightGBM model takes less time; the model considering the characteristics of the historical time window performs better than the other one, which can better improve the prediction accuracy of lane-changing behavior.
48
Wang, Hanqing, Xiaoyuan Wang, Junyan Han, et al. "A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning." Sensors 22, no. 2 (2022): 644. http://dx.doi.org/10.3390/s22020644.
Full textAbstract:
Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F1-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance.
49
Tselentis, Dimitrios I., and Eleonora Papadimitriou. "Driver Profile and Driving Pattern Recognition for Road Safety Assessment: Main Challenges and Future Directions." IEEE Open Journal of Intelligent Transportation Systems 4 (January 17, 2023): 83–100. https://doi.org/10.1109/OJITS.2023.3237177.
Full textAbstract:
This study reviews the Artificial Intelligence and Machine Learning approaches developed thus far for driver profile and driving pattern recognition, representing a set of macroscopic and microscopic behaviors respectively, to enhance the understanding of human factors in road safety, and therefore reduce the number of crashes. It provides a definition of the two scientific fields in terms of safety, and identifies the most efficient approaches used regarding methodology, data collection and driving metrics. Results show that K-means and Neural Networks are the most commonly used methodologies for driver profile identification, and Dynamic Time Warping for driving pattern detection. Most studies discovered driver profiles related to aggressiveness, considering mainly speed and acceleration as driving metrics. Based on the gaps and challenges identified, this paper provides a new framework for combining microscopic and macroscopic driving behavior analysis, instead of examining them separately as is the state-of-theart. Such combined results can potentially improve the development of traffic risk models, which could be exploited in applications that monitor drivers in real-time and provide feedback. These models will represent human behavior more accurately, which can eventually lead to the recognition of “optimal” human driving patterns that Automated Vehicles (AV) could ‘mimic’ to become safer.
50
Su, Jingjun. "Construction and Research of Machine Learning-based Pedal Misoperation Recognition Method." Advances in Engineering Technology Research 10, no. 1 (2024): 470. http://dx.doi.org/10.56028/aetr.10.1.470.2024.
Full textAbstract:
Background: A large number of traffic accidents are caused by drivers mistakenly stepping on the pedal in emergencies, highlighting an urgent concern about reducing pedal misoperation of drivers. Nowadays, machine learning has been widely applied in the fields of automatic driving, vehicle-circuit coordination, automatic obstacle avoidance, etc. However, the detection technology that focuses on the driver’s driving behavior during driving has not yet been able to greatly reduce the occurrence of traffic accidents. Purpose: Data collected by Chang’an University’s comprehensive driving behavior test platform were used to recognize whether a car driver has the behavior of pedal misoperation by developing and comparing a variety of machine learning algorithms. This paper proposes a method based on machine learning algorithms that takes into account the visual characteristics of the driver to identify pedal misoperation. Research methods: Five different machine learning algorithms were compared for the behavioral judgment of pedal misoperation of drivers through multiple evaluation indexes. Then, the performance of each algorithm was evaluated. As verified, the RandomForest algorithm outperforms all other algorithms with an accuracy rate of 98.4%.Conclusion: According to the research results, a method for recognizing the pedal misoperation behavior of drivers based on the RandomForest algorithm considering visual characteristics can more accurately recognize whether there is a pedal misoperation behavior.