Algorithm Design of Early Warning Seatbelt Intelligent Adjustment System Based on Neural Network and Big Data Analysis
With the purpose to guarantee the safety of drivers and passengers as well as lower the death rate collision, the early warning seatbelt intelligent adjustment system is designed by using big data analysis technology based on the aspects of hardware equipment, database, and software program. In the...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2020-01-01
|
| Series: | Mathematical Problems in Engineering |
| Online Access: | http://dx.doi.org/10.1155/2020/7268963 |
| Summary: | With the purpose to guarantee the safety of drivers and passengers as well as lower the death rate collision, the early warning seatbelt intelligent adjustment system is designed by using big data analysis technology based on the aspects of hardware equipment, database, and software program. In the hardware system, microcontroller AT89C52 is applied as the control core. By means of the sensor detection and drive control, the early warning safety belt tightening, locking and lifting, and other functions are realized. Meanwhile, various components of the hardware system are coordinated through debugging several modules in the hardware system and using the modified circuit to connect them together. We determine the relational rules of the database and create the corresponding database table, to provide sufficient data support for the realization of software functions. Using the big data analysis method to process the real-time detection data received by the sensor, the software functions such as timely tightening of safety belt, humidity relaxation, and over-rolling prevention can be realized according to different driving conditions of drivers and vehicles, respectively. The conclusion is drawn through the system test experiment: compared with the traditional regulation system, the design system has a higher degree of regulation, and the application of the design results to the actual vehicle can reduce the crash fatality rate of about 22.4%. |
|---|---|
| ISSN: | 1024-123X 1563-5147 |