Intelligent algorithm in a smart wearable device for predicting and alerting in the danger of vehicle collision
- PDF / 1,923,179 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 73 Downloads / 154 Views
ORIGINAL RESEARCH
Intelligent algorithm in a smart wearable device for predicting and alerting in the danger of vehicle collision Zexue Wang1 · Qidong Wan1 · Yangmei Qin1 · Senqing Fan1 · Zeyi Xiao1 Received: 17 May 2019 / Accepted: 28 November 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract We have designed a smart wearable device to protect actively pedestrian from impact of vehicle. This device consists of several modules, including radar sensor, transmission module, alarm module and intelligent security program module. In the dominant program module, the safety intelligent algorithm based on fuzzy comprehensive evaluation and BP neural network is proposed. From the perspective of a pedestrian, the moving data sensed by radar, combining with multiple effects of local surroundings, people and vehicles, road and transportation situation, weather, physiological and psychological situation of the pedestrian, are used as the data source for the algorithm. Based on the weight of the index determined by BP neural network, we use the fuzzy comprehensive evaluation to calculate the vehicle risk index. The smart wearable device can effectively predict and warn the situation of vehicles impacting pedestrians. The simulation has confirmed the accuracy of the prewarning algorithm under various conditions. Keywords Active protection algorithm · Vehicle impact · Precise alarm · Wearable device
1 Introduction In traffic accidents, pedestrians are usually in a weak position. Because in traffic system, the slow traffic participants are vulnerable to road accidents due to the lack of relevant protection measures (Hu et al. 2018). The urgency of avoiding or alleviating the injury to pedestrians is becoming more and more prominent. According to the National Bureau of Statistics of China, the number of pedestrian traffic safety accidents has generally increased since 2012, from 2063 in 2012 to 2740 in 2017. With the rapid growth of the number of vehicles and the increasingly tough traffic safety situation, an intelligent wearable device with dangerous vehicle alarm system should be designed for pedestrians to improve their safety. In recent years, with the breakthrough of micro millimeter wave radar technology, it has laid a foundation for the realization of the Prewarning system (Kishida et al. 2015). Therefore, how to use radar data and other sensors to predict vehicle threat is of great importance.
* Zeyi Xiao [email protected] 1
School of Chemical Engineering, Sichuan University, No. 24 South Section 1, Yihuan Road, Chengdu 610065, China
In recent years, many researchers have proposed a variety of protection methods for pedestrian safety, from both driver and vehicle. As for a driver, the safety system can prevent collisions by actively braking of the vehicle by analyzing the reliability of driver’s dynamic visual field (Morando et al. 2016), fatigue driving (Aidman et al. 2015; McDonald et al. 2018; Shi et al. 2014), emotional state detection (Katsis et al. 2011) and other factors(Jiang et al.
Data Loading...
