Kai Cao

Bio: Kai Cao is an academic researcher from Shandong University of Technology. The author has an hindex of 1, co-authored 2 publications receiving 3 citations.

Prediction Method of Driver’s Propensity Adapted to Driver’s Dynamic Feature Extraction of Affection

Abstract: Driver’s propensity is a dynamic measurement of driver’s characteristics, such as affection and preference. In the vehicle driver-assistance system, especially its collision warning subsystem, it is also an important parameter of computing driver's intention. The prediction of driver’s propensity from relative static and macroscopic perspective is an essential precondition for further researching and extracting dynamic characteristics. Physiology and psychology tests are designed to measure driver’s character and calculate physiological rhythm. Changing data of driver’s psychology and emotion during driving are obtained by real vehicle test. Then driver’s propensity values of different types are calculated by weighting method according to the contribution rate of standard features. Results show that this method is better than the traditional psychology test, and it provides a basis for further studying dynamic characteristics of driver’s affection.

Extraction of the Dynamic Vehicle Driver's Tendency Feature Based on Car-Following

Abstract: The influence of the driver's physiological and psychological characteristics on traffic safety is mainly represented as driver's tendency. Previous research about the driver's tendency mostly focused on the influence on traffic safety and the driver's psychological characteristics from a relative static and macroscopic perspective. In this paper, the Multi-Sensor Real-time Information Gathering Systems and the car-following experiments are designed to collect dynamic information about driver's behavior, vehicle state, traffic environment, etc., to compute driver's tendency. The data is divided into groups and ran through BP Neural Networks to obtain the correct classification rate for estimation. The characteristics of driver's tendency are extracted from a great number of samples through the Discrete Particle Swarm Optimization Method.

Dynamic Recognition of Driver’s Propensity Based on GPS Mobile Sensing Data and Privacy Protection

Abstract: Driver’s propensity is a dynamic measurement of driver’s emotional preference characteristics in driving process. It is a core parameter to compute driver’s intention and consciousness in safety driving assist system, especially in vehicle collision warning system. It is also an important influence factor to achieve the Driver-Vehicle-Environment Collaborative Wisdom and Control macroscopically. In this paper, dynamic recognition model of driver’s propensity based on support vector machine is established taking the vehicle safety controlled technology and respecting and protecting the driver’s privacy as precondition. The experiment roads travel time obtained through GPS is taken as the characteristic parameter. The sensing information of Driver-Vehicle-Environment was obtained through psychological questionnaire tests, real vehicle experiments, and virtual driving experiments, and the information is used for parameter calibration and validation of the model. Results show that the established recognition model of driver’s propensity is reasonable and feasible, which can achieve the dynamic recognition of driver’s propensity to some extent. The recognition model provides reference and theoretical basis for personalized vehicle active safety systems taking people as center especially for the vehicle safety technology based on the networking.

A Real-Time Recognition System of Driving Propensity Based on AutoNavi Navigation Data

Abstract: Driving propensity is the driver’s attitude towards the actual traffic situation and the corresponding decision-making or behavior during the driving process. It is of great significance to improve the accuracy of safety early warning and reduce traffic accidents. In this paper, a real-time identification system of driving propensity based on AutoNavi navigation data is proposed. The main work includes: (1) A dynamic data acquisition method of AutoNavi navigation is proposed to obtain the time, speed and acceleration of the driver during the navigation process. (2) The dynamic data collection method of AutoNavi navigation is analyzed and verified through the dynamic data obtained in the real vehicle experiment. The principal component analysis method is used to process the experimental data to extract the driving propensity characteristics variables. (3) The fruit fly optimization algorithm combined with GRNN (generalized neural network) and the feature variable set are used to build a FOA-GRNN-based model. The results show that the overall accuracy of the model can reach 94.17%. (4) A driving propensity identification system is constructed. The system has been verified through real vehicle test experiments. This paper provides a novel and convenient method for building personalized intelligent driver assistance systems in practical applications.

An In-Vehicle Application Providing System Based on Driver’s Biodata

Abstract: The recent technologies for vehicular networks including wireless communication have allowed vehicles to provide biosensor based various applications to a driver. This paper proposes a system to provide a driver with the application which the driver wants in a vehicle using driver’s biodata. The proposed system is composed of four components including a sensing unit, an inference unit, an application providing unit, and vehicular network unit. In this paper, the experiments were performed for correlation investigation between the number of biodata and the reliability of driver’s characteristics extraction. We found that the number of the data used had a significant influence on improving the driver’s satisfaction level, playing an important role in reflecting driver’s status. Experiments using actual vehicles are conducted to examine the effectiveness of the proposed system, and the results are analyzed and discussed. The results on the investigation of detection of biodata in gasoline and diesel vehicles by the experiments are also given. We confirmed that the proposed sensing method was capable of accurate detection irrespective of vehicle mode and vehicle type.

Machine Learning Recognition Mechanism Based on WI-FI Signal Optimization in the Detection of Driver’s Emotional Fluctuations

Abstract: With the development of the automobile industry, the use of vehicles has become the most basic means of transportation in people’s daily life. However, due to the rapid increase in the number of vehicles, more and more drivers are causing traffic accidents due to emotional fluctuations during driving. In order to reduce the occurrence of this problem, the artificial intelligence machine learning mechanism under Industry 4.0 technology can currently capture and detect the instantaneous facial emotions of drivers during driving. Through the literature survey, it is found that in the machine learning mode, the existing mechanism mainly relies on human vision and biological signals sensors to identify the driver’s emotional fluctuations during driving. However, due to the frequent distortion of visual detection methods and the problems of invasiveness and privacy invasion of biological signals, the investment cost is relatively high. In order to solve the problems under the existing algorithm, this paper firstly formulates the corresponding emotional fluctuation recognition model according to the existing WI-FI signal detection principle and designs the antenna position according to the Fresnel zone to achieve the best signal acquisition effect. In addition, the driver’s action status while using the brake and accelerator is collected. The emotion recognition coefficient is calculated by the collected data, and the fluctuation recognition is performed by using the recognition wash and LSTM emotion discriminator. Finally, according to the evaluation data, the recognition rate of about 85% in the real scene is achieved.