Figure 4 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The proliferation of info-entertainment systems in nowadays vehicles has provided a really cheap and easy-to-deploy platform with the ability to gather information about the vehicle under analysis. With the purpose to provide an architecture to increase safety and security in automotive context, in this paper we propose a fully connected neural net...
Context in source publication
Context 1
... highlight that the proposed feature set can also be easily collected from cheap mobile devices equipped, for instance, with the Android operating systems, but also from the info-entertainment systems available in modern vehicles. Figure 4 depicts the flow diagram of the intelligence module in detail: . ...
Citations
... As identified in the literature review conducted, this is the first study to focus on the driving pulse level to identify patterns of driving behaviour around harsh events. Most studies in the past focused on driving style recognition using already classified events or maneuvers with the purpose of identifying the driver, the type of maneuvers or their intensity (Martinelli et al., 2021, Sarker et al., 2021, Schwarz 2017. The difference between this and these past studies is that our study uses an unsupervised learning approach, and not a supervised learning approach that assumes prior knowledge on what each pattern represents and in which cluster it belongs to. ...
... Additionally, there were more than 50 parameters that could be gathered from the ECU and can be used for a variety of purposes, including determining how a driver or operator behaves and making pertinent suggestions or recommendations to them, providing information and warnings about preventive and scheduled maintenance, and providing data that an insurance company can use to process claims. A few of these systems also used additional sensors and devices such as smartphones for implementation and analysis [12][13][14]. ...
The transportation industry’s focus on improving performance and reducing costs has driven the integration of IoT and machine learning technologies. The correlation between driving style and behavior with fuel consumption and emissions has highlighted the need to classify different driver’s driving patterns. In response, vehicles now come equipped with sensors that gather a wide range of operational data. The proposed technique collects critical vehicle performance data, including speed, motor RPM, paddle position, determined motor load, and over 50 other parameters through the OBD interface. The OBD-II diagnostics protocol, the primary diagnostic process used by technicians, can acquire this information via the car’s communication port. OBD-II protocol is used to acquire real-time data linked to the vehicle’s operation. This data are used to collect engine operation-related characteristics and assist with fault detection. The proposed method uses machine learning techniques, such as SVM, AdaBoost, and Random Forest, to classify driver’s behavior based on ten categories that include fuel consumption, steering stability, velocity stability, and braking patterns. The solution offers an effective means to study driving behavior and recommend corrective actions for efficient and safe driving. The proposed model offers a classification of ten driver classes based on fuel consumption, steering stability, velocity stability, and braking patterns. This research work uses data extracted from the engine’s internal sensors via the OBD-II protocol, eliminating the need for additional sensors. The collected data are used to build a model that classifies driver’s behavior and can be used to provide feedback to improve driving habits. Key driving events, such as high-speed braking, rapid acceleration, deceleration, and turning, are used to characterize individual drivers. Visualization techniques, such as line plots and correlation matrices, are used to compare drivers’ performance. Time-series values of the sensor data are considered in the model. The supervised learning methods are employed to compare all driver classes. SVM, AdaBoost, and Random Forest algorithms are implemented with 99%, 99%, and 100% accuracy, respectively. The suggested model offers a practical approach to examining driving behavior and suggesting necessary measures to enhance driving safety and efficiency.
... Rights reserved. methods [2,23] and deep learning methods [25,35]. Precious works are mainly based on classic machine learning methods such as random forest (RF) [29], support vector machine (SVM) [10] and k-nearest neighbor (k-NN) [50]. ...
Driving style detection is an essential real-world requirement in diverse contexts, such as traffic safety, car insurance and fuel consumption optimization. However, the existing methods either rely on handcrafted features or fail to explore deep spatial-temporal features from multi-modal sensing signals. In this paper, we propose a novel attention-based hybrid convolutional neural network (CNN) and long short-term memory (LSTM) framework named DSDCLA to address these problems. Specifically, DSDCLA first introduces CNN and self-attention for extracting local spatial features from multi-modal driving sequences. Then, we utilize LSTM and multi-head attention to explore the long-term temporal relationships between timesteps. Therefore, DSDCLA can identify driving style by short- and long-term spatial-temporal features. Furthermore, we design three variants with different levels of fusion, which shows the advantage of selecting components and improves the interpretability. We extensively evaluated the proposed DSDCLA on two public real-world datasets, and the experimental results show that DSDCLA outperforms the current state-of-the-art methods, achieving the F1-scores of 97.03% and 97.65%. Numerous ablation studies and visualizations indicate the effectiveness of the model and the importance of multi-level attention fusion for identifying driving style between timesteps.
... A total of 14 participants participated in the experiment and each of them performed two to three sessions (40 conducted overall), which were 20 minutes long. Naturalistic experiment using CAN Bus system [12] Naturalistic experiment [51] Naturalistic driving experiment 18 drivers [51] Naturalistic driving data 105 hours of bus loggings -9 cars -16 days -4 countries [53] Naturalistic driving data from enhanced CAN bus 50Hz [54] Naturalistic datasets [55] Naturalistic experiment [57] Naturalistic experiment [11] Naturalistic experiment 7 months -6,000 trips [58] Naturalistic experiment 30 drivers [59] Naturalistic experiment [60] Naturalistic experiment 16 drivers minmore than 1000 min driving [61] Naturalistic dataset 89 drivers -10,108 events [62] Naturalistic experiment ...
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-the-art. 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.
The majority of traffic accidents are caused by human drowsiness, weariness and absentmindedness. ML “Machine learning” technology has recently been used to accurately identify styles of driving and recognise risky DB “Driving Behaviour” using signals of Inside Car sensors “In-Car sensors”. For example speed of engine and car, position of throttles, load on engine during driving. Through detailed study and analysis we brainstormed the prominence of fusion and blend various Outside Car sensors “Out-Car sensors”, like GPS, magnetometer or a gyrometer with In-Car sensors in order to yield enhanced accuracy in identification of DB style. The proposed integration of In-Car and Out-Car sensors will enhance ML identification of unsafe DB. From Out-Car sensors a set of capable features can be computed which may precisely portray the DB. The factual data may be utilized to assess classification performances through a specific target strategy dependent on the connection among car speed, longitudinal acceleration and lateral longitudinal acceleration of car. Based on this technical fusion of ML and Out-Car sensors the potential capability of system can definitely take an accuracy leap in identification of unsafe DB. In this paper, we first discuss the idea of risky driving behaviour and the significance of technology in helping safe driving, followed by a review of related work in the field of DB identification. Following that, we propose our sensor fusion technology for improving DB identification or detection results. We go over numerous In-Car/Out-of-Car sensors and discuss the performance matrix. Finally, this study highlights the paper's conclusion and future scope of work in this area, which may contribute in further enhancing the precision of DB identification results.
This paper first introduces the BP neural network, upgrades and optimizes the neural network according to the actual demand, and then establishes the prediction model of vehicle braking deceleration according to the relevant parameters affecting vehicle deceleration. According to the vehicle relative distance, vehicle relative speed, front vehicle acceleration, collision time and lateral distance, the vehicle deceleration is predicted and analyzed. After data verification, the vehicle braking deceleration prediction model is more accurate for vehicle deceleration prediction, and the established prediction model is effective.
