Driving maneuver classification from time series data: a rule based machine learning approach

Haque, Md. Mokammel; Sarker, Supriya; Dewan, M. Ali Akber

doi:10.1007/s10489-022-03328-3

Cited by 8 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI is a core enabler in identifying hidden data patterns, emerging correlations, and abnormal behaviors to gain knowledge from real-time data sources and make data-driven decisions for better outcomes [52]. It covers multiple technologies and methods powered by advanced tools for several purposes.…”

Section: Edge Ai Implementationmentioning

confidence: 99%

Edge AI-Assisted IoV Application for Aggressive Driver Monitoring: A Case Study on Public Transport Buses

SOY

2023

International Journal of Automotive Science and Technology

View full text Add to dashboard Cite

With increasing adoption of digital technologies to automotive industry, the revo-lution of the vehicles opens new doors for many advanced applications to improve the driver safety and comfort. Thanks to Advanced Driver Assistance Systems (ADAS), no doubt that the future driving experience will be safer than today. De-spite the emergence of new trends, road accidents caused by aggressive driving are still a major problem in many countries. This study presents an edge AI-assisted ag-gressive driver monitoring system based on Internet of Vehicles (IoV) model. In the proposed system, the kNN algorithm and dynamic time warping method are used to recognize the signal patterns of aggressive drivers. The hardware platform is built on the RP2040 microcontroller-based Raspberry Pi Pico board and the Waveshare Quad Expander used for sensor extensions. The MPU-9250 9-axis motion tracking sensor is used as an inertial measurement unit (IMU) to identify the patterns of driv-ers who did sudden lane changes, heavy acceleration, and harsh braking on the roads. Besides, the required software is created using the MicroPython scripting language via Thonny IDE. The proposed method is tested on public transport vehi-cles to determine the drivers engaging in dangerous driving behavior for passengers. The obtained results show that the proposed method can provide satisfactory success to support for recognizing the aggressive behavior of drivers.

show abstract

Section: Edge Ai Implementationmentioning

confidence: 99%

Edge AI-Assisted IoV Application for Aggressive Driver Monitoring: A Case Study on Public Transport Buses

SOY

2023

International Journal of Automotive Science and Technology

View full text Add to dashboard Cite

show abstract

“…Self-Organizing Map (SOM) [41] Fuzed & Hybrid Models Multi-Source Data Fusion [43] Fusing CNN and RNN with an attention mechanism [44] (CNN-LSTM) [45] Transfer Learning Transfer Learning methods for temporal data [86] Offline Methods…”

Section: Time Series Data Analysis Techniques Using Motifsmentioning

confidence: 99%

“…Several Deep unsupervised learning approaches, including self-organizing map (SOM), deep autoencoders, and partitive clustering algorithms, were successfully applied for detecting drivers' behavior [41].…”

Section: Introductionmentioning

confidence: 99%

Driver Behavior Detection in Time Series Decade review

Saber,

Ghoniemy,

Al-Qutt

2023

IJICIS

View full text Add to dashboard Cite

Driver's behavior is expressed by the intentional and unintentional actions the driver performs while driving a motor vehicle. This behavior could be influenced by several factors such as fatigue, drowsiness, vehicle surroundings, and distraction state. Driver's behavior could be normal, risky or aggressive. Risky and aggressive behaviors, such as harsh braking and rapid acceleration, can lead to traffic accidents. Monitoring, analyzing and improving driver's behavior can reduce traffic collisions and enhance road safety. Different approaches have been followed for the detection and identification of driver's behavior. Rule-based Machine learning (ML) and deep learning (DL) approaches have succeeded to mine dynamical characteristics of time series. However, they have some challenges that make them unsuitable for many classification tasks including the selection of efficient architectures and corresponding hyper-parameters, as well as slow training and limited labeled data. Fusion and attention mechanisms through hybrid approaches were found to be more suitable for time series sensor data analysis. Transfer learning addresses useful approaches for making use of learning applied to other applications. Maneuver detection represents a serious characteristic of driver's behavior identification. A recent approach for extracting maneuvers from high-frequency telematics data is through time series motifs detection algorithms. Motifs extraction is preferred over ML and DL approaches as it does not requie labels, which is extremely time-consuming to collect. This work focuses on the latest techniques for classifying driver's behavior in time series data, and summarizes the pros and cons of the different categories.

show abstract

“…The rule-based classifier uses indictors such as convergency and accuracy to delete and fuse pre-set simple rules to obtain the final classification rules. Based on these rules, driving variables such as longitudinal acceleration and yaw angle were filtered, driving behaviors such as lane changes were successfully recognized [20]. However, efficient rule-based classifiers require a rich technical experience for researchers, and they have limited applicability.…”

Section: Introductionmentioning

confidence: 99%

Driving Behavior Primitive Classification Using CNN-Based Fusion Models

Cui,

Li,

Zheng

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Driving behavior primitives play a crucial role in semantic explanation of driving behaviors. Although much work has been done on exacting driving behavior primitives from naturalistic driving data, few studies was published on primitive classification. Driving behavior primitives are typically described by multi-dimensional variables with varying durations, which leads to the inefficiency of the traditional classification methods. There hence, a CNN-based fusion model for primitive classification is proposed in this paper. Primitive feature matrix is constructed using statistical methods for the four basic and the four constructed variables, which serves as the input. A 1D-CNN is employed to extract global information of the total eight variables in the feature matrix, while a 2D-CNN is used to extract the local information. The 1D-CNN and the 2D-CNN are fused in parallel using a new fusion method to combine different types of information, and two models, namely the FC-before fusion model and the FC-after fusion model, are acquired. Compared with the classical methods, the empirical results demonstrate that CNN-based fusion model can recognize driving behavior primitives more accurately. Specifically, the FC-after fusion model achieves an accuracy of 91.12% and a macro F1-score of 90.88%, while the accuracy and macro F1-score of the FCbefore fusion model are 93.47% and 92.57%, respectively. INDEX TERMSDriving behavior semantics, Driving behavior primitive classification, Deep learning, CNN-based fusion model.

show abstract

Driving maneuver classification from time series data: a rule based machine learning approach

Cited by 8 publications

References 46 publications

Edge AI-Assisted IoV Application for Aggressive Driver Monitoring: A Case Study on Public Transport Buses

Edge AI-Assisted IoV Application for Aggressive Driver Monitoring: A Case Study on Public Transport Buses

Driver Behavior Detection in Time Series Decade review

Driving Behavior Primitive Classification Using CNN-Based Fusion Models

Contact Info

Product

Resources

About